/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/fd4730dd8aad/Qwen3.8-27B-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.099.596 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.099.655 I srv llama_server: initializing ... 0.00.099.660 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.099.744 I srv init_listene: The UI is disabled 0.00.099.745 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.099.779 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.101.435 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/fd4730dd8aad/Qwen3.8-27B-UD-Q2_K_XL.gguf' 0.00.631.486 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.631.496 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.631.503 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.631.506 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.631.508 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.631.516 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.631.518 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.631.520 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.631.522 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.631.524 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.631.526 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.631.529 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.631.532 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.631.534 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.631.541 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.204.438 I cmn init: llama threadpool init, n_threads = 8 0.01.618.019 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.621.880 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.621.894 I srv llama_server: model loaded 0.01.621.901 I srv llama_server: listening on http://127.0.0.1:8091 0.31.595.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.595.238 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.31.595.239 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.595.251 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 0.31.595.251 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.595.263 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.31.595.264 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.595.276 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.37.267.048 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.67 s / 19.57 tokens per second 0.37.450.395 I slot print_timing: id 1 | task 1 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.67 s / 20.80 tokens per second 0.37.462.031 I slot print_timing: id 2 | task 3 | prompt processing, n_tokens = 126, progress = 0.97, t = 5.67 s / 22.22 tokens per second 0.37.473.587 I slot print_timing: id 3 | task 2 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.67 s / 19.57 tokens per second 0.38.283.166 I slot print_timing: id 0 | task 0 | prompt eval time = 6402.99 ms / 115 tokens ( 55.68 ms per token, 17.96 tokens per second) 0.38.283.171 I slot print_timing: id 0 | task 0 | eval time = 284.89 ms / 2 tokens ( 284.89 ms per token, 3.51 tokens per second) 0.38.283.171 I slot print_timing: id 0 | task 0 | total time = 6687.88 ms / 117 tokens 0.38.283.171 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.38.283.172 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.283.190 I slot release: id 0 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.38.283.343 I slot print_timing: id 1 | task 1 | prompt eval time = 6403.31 ms / 122 tokens ( 52.49 ms per token, 19.05 tokens per second) 0.38.283.346 I slot print_timing: id 1 | task 1 | eval time = 284.75 ms / 2 tokens ( 284.75 ms per token, 3.51 tokens per second) 0.38.283.347 I slot print_timing: id 1 | task 1 | total time = 6688.05 ms / 124 tokens 0.38.283.347 I slot print_timing: id 1 | task 1 | graphs reused = 1 0.38.283.347 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.283.358 I slot release: id 1 | task 1 | stop processing: n_tokens = 123, truncated = 0 0.38.283.531 I slot print_timing: id 2 | task 3 | prompt eval time = 6403.65 ms / 130 tokens ( 49.26 ms per token, 20.30 tokens per second) 0.38.283.536 I slot print_timing: id 2 | task 3 | eval time = 284.58 ms / 2 tokens ( 284.58 ms per token, 3.51 tokens per second) 0.38.283.536 I slot print_timing: id 2 | task 3 | total time = 6688.24 ms / 132 tokens 0.38.283.536 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.38.283.536 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.283.548 I slot release: id 2 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.38.283.721 I slot print_timing: id 3 | task 2 | prompt eval time = 6404.01 ms / 115 tokens ( 55.69 ms per token, 17.96 tokens per second) 0.38.283.730 I slot print_timing: id 3 | task 2 | eval time = 284.41 ms / 2 tokens ( 284.41 ms per token, 3.52 tokens per second) 0.38.283.730 I slot print_timing: id 3 | task 2 | total time = 6688.42 ms / 117 tokens 0.38.283.730 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.38.283.731 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.283.740 I slot release: id 3 | task 2 | stop processing: n_tokens = 116, truncated = 0 0.38.293.009 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.236 0.38.315.368 I slot launch_slot_: id 1 | task 7 | processing task, is_child = 0 0.38.382.083 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.221 0.38.382.157 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.38.382.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.38.382.223 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.38.382.248 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.38.382.276 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.45.064.952 I slot print_timing: id 0 | task 9 | prompt processing, n_tokens = 156, progress = 0.97, t = 6.68 s / 23.34 tokens per second 0.45.831.174 I slot print_timing: id 1 | task 7 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.68 s / 15.56 tokens per second 0.45.835.690 I slot print_timing: id 2 | task 8 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.68 s / 22.15 tokens per second 0.45.840.460 I slot print_timing: id 3 | task 10 | prompt processing, n_tokens = 196, progress = 0.98, t = 6.68 s / 29.33 tokens per second 0.46.417.825 I slot print_timing: id 0 | task 9 | prompt eval time = 7825.57 ms / 160 tokens ( 48.91 ms per token, 20.45 tokens per second) 0.46.417.827 I slot print_timing: id 0 | task 9 | eval time = 209.97 ms / 2 tokens ( 209.97 ms per token, 4.76 tokens per second) 0.46.417.827 I slot print_timing: id 0 | task 9 | total time = 8035.54 ms / 162 tokens 0.46.417.827 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.46.417.828 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.417.847 I slot release: id 0 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.46.418.004 I slot print_timing: id 1 | task 7 | prompt eval time = 7825.71 ms / 108 tokens ( 72.46 ms per token, 13.80 tokens per second) 0.46.418.009 I slot print_timing: id 1 | task 7 | eval time = 210.00 ms / 2 tokens ( 210.00 ms per token, 4.76 tokens per second) 0.46.418.010 I slot print_timing: id 1 | task 7 | total time = 8035.71 ms / 110 tokens 0.46.418.010 I slot print_timing: id 1 | task 7 | graphs reused = 1 0.46.418.010 I slot print_timing: id 1 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.418.021 I slot release: id 1 | task 7 | stop processing: n_tokens = 109, truncated = 0 0.46.418.195 I slot print_timing: id 2 | task 8 | prompt eval time = 7825.87 ms / 152 tokens ( 51.49 ms per token, 19.42 tokens per second) 0.46.418.200 I slot print_timing: id 2 | task 8 | eval time = 210.01 ms / 2 tokens ( 210.01 ms per token, 4.76 tokens per second) 0.46.418.201 I slot print_timing: id 2 | task 8 | total time = 8035.89 ms / 154 tokens 0.46.418.201 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.46.418.201 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.418.210 I slot release: id 2 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.46.418.394 I slot print_timing: id 3 | task 10 | prompt eval time = 7826.02 ms / 200 tokens ( 39.13 ms per token, 25.56 tokens per second) 0.46.418.397 I slot print_timing: id 3 | task 10 | eval time = 210.05 ms / 2 tokens ( 210.05 ms per token, 4.76 tokens per second) 0.46.418.397 I slot print_timing: id 3 | task 10 | total time = 8036.07 ms / 202 tokens 0.46.418.397 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.46.418.398 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.418.408 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.46.424.340 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.174 0.46.446.943 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.46.514.275 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.266 0.46.514.351 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.46.514.400 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.183 0.46.514.433 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.46.514.453 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.46.514.486 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.52.487.984 I slot print_timing: id 0 | task 14 | prompt processing, n_tokens = 113, progress = 0.97, t = 5.97 s / 18.92 tokens per second 0.52.918.359 I slot print_timing: id 1 | task 15 | prompt processing, n_tokens = 114, progress = 0.97, t = 5.97 s / 19.08 tokens per second 0.52.922.801 I slot print_timing: id 2 | task 16 | prompt processing, n_tokens = 121, progress = 0.97, t = 5.97 s / 20.26 tokens per second 0.52.927.212 I slot print_timing: id 3 | task 17 | prompt processing, n_tokens = 146, progress = 0.97, t = 5.97 s / 24.44 tokens per second 0.53.503.904 I slot print_timing: id 0 | task 14 | prompt eval time = 6779.40 ms / 117 tokens ( 57.94 ms per token, 17.26 tokens per second) 0.53.503.909 I slot print_timing: id 0 | task 14 | eval time = 210.01 ms / 2 tokens ( 210.01 ms per token, 4.76 tokens per second) 0.53.503.910 I slot print_timing: id 0 | task 14 | total time = 6989.41 ms / 119 tokens 0.53.503.910 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.53.503.910 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.503.927 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.53.504.082 I slot print_timing: id 1 | task 15 | prompt eval time = 6779.55 ms / 118 tokens ( 57.45 ms per token, 17.41 tokens per second) 0.53.504.084 I slot print_timing: id 1 | task 15 | eval time = 210.02 ms / 2 tokens ( 210.02 ms per token, 4.76 tokens per second) 0.53.504.085 I slot print_timing: id 1 | task 15 | total time = 6989.57 ms / 120 tokens 0.53.504.085 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.53.504.085 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.504.095 I slot release: id 1 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.53.504.261 I slot print_timing: id 2 | task 16 | prompt eval time = 6779.72 ms / 125 tokens ( 54.24 ms per token, 18.44 tokens per second) 0.53.504.262 I slot print_timing: id 2 | task 16 | eval time = 210.02 ms / 2 tokens ( 210.02 ms per token, 4.76 tokens per second) 0.53.504.263 I slot print_timing: id 2 | task 16 | total time = 6989.74 ms / 127 tokens 0.53.504.263 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.53.504.263 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.504.273 I slot release: id 2 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.53.504.432 I slot print_timing: id 3 | task 17 | prompt eval time = 6779.89 ms / 150 tokens ( 45.20 ms per token, 22.12 tokens per second) 0.53.504.435 I slot print_timing: id 3 | task 17 | eval time = 210.01 ms / 2 tokens ( 210.01 ms per token, 4.76 tokens per second) 0.53.504.435 I slot print_timing: id 3 | task 17 | total time = 6989.90 ms / 152 tokens 0.53.504.435 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.53.504.438 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.504.448 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.53.510.919 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.237 0.53.533.160 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.53.599.953 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.235 0.53.600.032 I slot launch_slot_: id 1 | task 21 | processing task, is_child = 0 0.53.600.071 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.222 0.53.600.109 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.53.600.128 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.53.600.161 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.59.947.573 I slot print_timing: id 0 | task 22 | prompt processing, n_tokens = 139, progress = 0.97, t = 6.35 s / 21.90 tokens per second 1.00.726.202 I slot print_timing: id 1 | task 21 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.35 s / 20.80 tokens per second 1.00.730.793 I slot print_timing: id 2 | task 23 | prompt processing, n_tokens = 115, progress = 0.97, t = 6.35 s / 18.12 tokens per second 1.00.735.628 I slot print_timing: id 3 | task 24 | prompt processing, n_tokens = 177, progress = 0.98, t = 6.35 s / 27.89 tokens per second 1.01.313.521 I slot print_timing: id 0 | task 22 | prompt eval time = 7503.19 ms / 143 tokens ( 52.47 ms per token, 19.06 tokens per second) 1.01.313.522 I slot print_timing: id 0 | task 22 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 1.01.313.523 I slot print_timing: id 0 | task 22 | total time = 7713.35 ms / 145 tokens 1.01.313.523 I slot print_timing: id 0 | task 22 | graphs reused = 1 1.01.313.524 I slot print_timing: id 0 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.313.542 I slot release: id 0 | task 22 | stop processing: n_tokens = 144, truncated = 0 1.01.313.698 I slot print_timing: id 1 | task 21 | prompt eval time = 7503.36 ms / 136 tokens ( 55.17 ms per token, 18.13 tokens per second) 1.01.313.701 I slot print_timing: id 1 | task 21 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 1.01.313.702 I slot print_timing: id 1 | task 21 | total time = 7713.52 ms / 138 tokens 1.01.313.702 I slot print_timing: id 1 | task 21 | graphs reused = 1 1.01.313.702 I slot print_timing: id 1 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.313.720 I slot release: id 1 | task 21 | stop processing: n_tokens = 137, truncated = 0 1.01.313.896 I slot print_timing: id 2 | task 23 | prompt eval time = 7503.52 ms / 119 tokens ( 63.05 ms per token, 15.86 tokens per second) 1.01.313.897 I slot print_timing: id 2 | task 23 | eval time = 210.17 ms / 2 tokens ( 210.17 ms per token, 4.76 tokens per second) 1.01.313.898 I slot print_timing: id 2 | task 23 | total time = 7713.69 ms / 121 tokens 1.01.313.898 I slot print_timing: id 2 | task 23 | graphs reused = 1 1.01.313.898 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.313.907 I slot release: id 2 | task 23 | stop processing: n_tokens = 120, truncated = 0 1.01.314.096 I slot print_timing: id 3 | task 24 | prompt eval time = 7503.69 ms / 181 tokens ( 41.46 ms per token, 24.12 tokens per second) 1.01.314.099 I slot print_timing: id 3 | task 24 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 1.01.314.100 I slot print_timing: id 3 | task 24 | total time = 7713.88 ms / 183 tokens 1.01.314.102 I slot print_timing: id 3 | task 24 | graphs reused = 1 1.01.314.102 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.314.112 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 1.01.320.169 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.194 1.01.347.278 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 1.01.406.487 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.204 1.01.406.562 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 1.01.406.599 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.233 1.01.409.898 I slot launch_slot_: id 2 | task 29 | processing task, is_child = 0 1.01.409.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.154 1.01.409.954 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 1.07.671.118 I slot print_timing: id 0 | task 28 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.26 s / 20.28 tokens per second 1.08.444.681 I slot print_timing: id 1 | task 30 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.26 s / 22.36 tokens per second 1.08.449.245 I slot print_timing: id 2 | task 29 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.26 s / 18.85 tokens per second 1.08.454.195 I slot print_timing: id 3 | task 31 | prompt processing, n_tokens = 174, progress = 0.98, t = 6.26 s / 27.79 tokens per second 1.09.032.180 I slot print_timing: id 0 | task 28 | prompt eval time = 7411.97 ms / 131 tokens ( 56.58 ms per token, 17.67 tokens per second) 1.09.032.183 I slot print_timing: id 0 | task 28 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 1.09.032.184 I slot print_timing: id 0 | task 28 | total time = 7622.22 ms / 133 tokens 1.09.032.184 I slot print_timing: id 0 | task 28 | graphs reused = 1 1.09.032.185 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.032.212 I slot release: id 0 | task 28 | stop processing: n_tokens = 132, truncated = 0 1.09.032.367 I slot print_timing: id 1 | task 30 | prompt eval time = 7412.15 ms / 144 tokens ( 51.47 ms per token, 19.43 tokens per second) 1.09.032.372 I slot print_timing: id 1 | task 30 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 1.09.032.373 I slot print_timing: id 1 | task 30 | total time = 7622.39 ms / 146 tokens 1.09.032.373 I slot print_timing: id 1 | task 30 | graphs reused = 1 1.09.032.374 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.032.384 I slot release: id 1 | task 30 | stop processing: n_tokens = 145, truncated = 0 1.09.032.558 I slot print_timing: id 2 | task 29 | prompt eval time = 7412.36 ms / 122 tokens ( 60.76 ms per token, 16.46 tokens per second) 1.09.032.559 I slot print_timing: id 2 | task 29 | eval time = 210.21 ms / 2 tokens ( 210.21 ms per token, 4.76 tokens per second) 1.09.032.560 I slot print_timing: id 2 | task 29 | total time = 7622.57 ms / 124 tokens 1.09.032.560 I slot print_timing: id 2 | task 29 | graphs reused = 1 1.09.032.560 I slot print_timing: id 2 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.032.573 I slot release: id 2 | task 29 | stop processing: n_tokens = 123, truncated = 0 1.09.032.743 I slot print_timing: id 3 | task 31 | prompt eval time = 7412.56 ms / 178 tokens ( 41.64 ms per token, 24.01 tokens per second) 1.09.032.745 I slot print_timing: id 3 | task 31 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 1.09.032.745 I slot print_timing: id 3 | task 31 | total time = 7622.75 ms / 180 tokens 1.09.032.745 I slot print_timing: id 3 | task 31 | graphs reused = 1 1.09.032.746 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.032.754 I slot release: id 3 | task 31 | stop processing: n_tokens = 179, truncated = 0 1.09.038.237 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.220 1.09.057.244 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 1.09.125.704 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.193 1.09.125.777 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 1.09.125.821 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 1.09.125.858 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 1.09.125.876 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.228 1.09.125.908 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 1.15.148.502 I slot print_timing: id 0 | task 36 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.02 s / 19.26 tokens per second 1.15.318.966 I slot print_timing: id 1 | task 35 | prompt processing, n_tokens = 109, progress = 0.96, t = 6.02 s / 18.10 tokens per second 1.15.323.552 I slot print_timing: id 2 | task 38 | prompt processing, n_tokens = 138, progress = 0.97, t = 6.02 s / 22.91 tokens per second 1.15.328.311 I slot print_timing: id 3 | task 37 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.02 s / 23.25 tokens per second 1.15.906.048 I slot print_timing: id 0 | task 36 | prompt eval time = 6570.37 ms / 120 tokens ( 54.75 ms per token, 18.26 tokens per second) 1.15.906.053 I slot print_timing: id 0 | task 36 | eval time = 209.75 ms / 2 tokens ( 209.75 ms per token, 4.77 tokens per second) 1.15.906.054 I slot print_timing: id 0 | task 36 | total time = 6780.12 ms / 122 tokens 1.15.906.054 I slot print_timing: id 0 | task 36 | graphs reused = 1 1.15.906.054 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.906.076 I slot release: id 0 | task 36 | stop processing: n_tokens = 121, truncated = 0 1.15.906.229 I slot print_timing: id 1 | task 35 | prompt eval time = 6570.51 ms / 113 tokens ( 58.15 ms per token, 17.20 tokens per second) 1.15.906.233 I slot print_timing: id 1 | task 35 | eval time = 209.77 ms / 2 tokens ( 209.77 ms per token, 4.77 tokens per second) 1.15.906.233 I slot print_timing: id 1 | task 35 | total time = 6780.28 ms / 115 tokens 1.15.906.233 I slot print_timing: id 1 | task 35 | graphs reused = 1 1.15.906.234 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.906.244 I slot release: id 1 | task 35 | stop processing: n_tokens = 114, truncated = 0 1.15.906.410 I slot print_timing: id 2 | task 38 | prompt eval time = 6570.67 ms / 142 tokens ( 46.27 ms per token, 21.61 tokens per second) 1.15.906.413 I slot print_timing: id 2 | task 38 | eval time = 209.78 ms / 2 tokens ( 209.78 ms per token, 4.77 tokens per second) 1.15.906.413 I slot print_timing: id 2 | task 38 | total time = 6780.45 ms / 144 tokens 1.15.906.414 I slot print_timing: id 2 | task 38 | graphs reused = 1 1.15.906.414 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.906.432 I slot release: id 2 | task 38 | stop processing: n_tokens = 143, truncated = 0 1.15.906.613 I slot print_timing: id 3 | task 37 | prompt eval time = 6570.83 ms / 144 tokens ( 45.63 ms per token, 21.92 tokens per second) 1.15.906.615 I slot print_timing: id 3 | task 37 | eval time = 209.81 ms / 2 tokens ( 209.81 ms per token, 4.77 tokens per second) 1.15.906.615 I slot print_timing: id 3 | task 37 | total time = 6780.64 ms / 146 tokens 1.15.906.616 I slot print_timing: id 3 | task 37 | graphs reused = 1 1.15.906.616 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.906.626 I slot release: id 3 | task 37 | stop processing: n_tokens = 145, truncated = 0 1.15.912.182 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.231 1.15.937.784 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 1.16.012.207 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.246 1.16.012.286 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 1.16.012.323 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.196 1.16.012.364 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 1.16.012.383 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.193 1.16.012.422 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 1.21.979.205 I slot print_timing: id 0 | task 42 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.97 s / 19.94 tokens per second 1.22.406.152 I slot print_timing: id 1 | task 43 | prompt processing, n_tokens = 139, progress = 0.97, t = 5.97 s / 23.30 tokens per second 1.22.410.562 I slot print_timing: id 2 | task 44 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.97 s / 18.10 tokens per second 1.22.415.001 I slot print_timing: id 3 | task 45 | prompt processing, n_tokens = 105, progress = 0.96, t = 5.97 s / 17.60 tokens per second 1.22.992.255 I slot print_timing: id 0 | task 42 | prompt eval time = 6769.65 ms / 123 tokens ( 55.04 ms per token, 18.17 tokens per second) 1.22.992.260 I slot print_timing: id 0 | task 42 | eval time = 210.17 ms / 2 tokens ( 210.17 ms per token, 4.76 tokens per second) 1.22.992.260 I slot print_timing: id 0 | task 42 | total time = 6979.82 ms / 125 tokens 1.22.992.261 I slot print_timing: id 0 | task 42 | graphs reused = 1 1.22.992.261 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.992.282 I slot release: id 0 | task 42 | stop processing: n_tokens = 124, truncated = 0 1.22.992.435 I slot print_timing: id 1 | task 43 | prompt eval time = 6769.85 ms / 143 tokens ( 47.34 ms per token, 21.12 tokens per second) 1.22.992.440 I slot print_timing: id 1 | task 43 | eval time = 210.15 ms / 2 tokens ( 210.15 ms per token, 4.76 tokens per second) 1.22.992.441 I slot print_timing: id 1 | task 43 | total time = 6979.99 ms / 145 tokens 1.22.992.441 I slot print_timing: id 1 | task 43 | graphs reused = 1 1.22.992.441 I slot print_timing: id 1 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.992.450 I slot release: id 1 | task 43 | stop processing: n_tokens = 144, truncated = 0 1.22.992.616 I slot print_timing: id 2 | task 44 | prompt eval time = 6770.03 ms / 112 tokens ( 60.45 ms per token, 16.54 tokens per second) 1.22.992.617 I slot print_timing: id 2 | task 44 | eval time = 210.13 ms / 2 tokens ( 210.13 ms per token, 4.76 tokens per second) 1.22.992.618 I slot print_timing: id 2 | task 44 | total time = 6980.16 ms / 114 tokens 1.22.992.618 I slot print_timing: id 2 | task 44 | graphs reused = 1 1.22.992.618 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.992.627 I slot release: id 2 | task 44 | stop processing: n_tokens = 113, truncated = 0 1.22.992.794 I slot print_timing: id 3 | task 45 | prompt eval time = 6770.22 ms / 109 tokens ( 62.11 ms per token, 16.10 tokens per second) 1.22.992.795 I slot print_timing: id 3 | task 45 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 1.22.992.796 I slot print_timing: id 3 | task 45 | total time = 6980.32 ms / 111 tokens 1.22.992.796 I slot print_timing: id 3 | task 45 | graphs reused = 1 1.22.992.796 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.992.809 I slot release: id 3 | task 45 | stop processing: n_tokens = 110, truncated = 0 1.22.998.925 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.226 1.23.025.090 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 1.23.122.976 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 1.23.123.037 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 1.23.123.074 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.194 1.23.126.479 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 1.23.126.502 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.255 1.23.126.535 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 1.28.852.296 I slot print_timing: id 0 | task 49 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.73 s / 17.12 tokens per second 1.29.281.379 I slot print_timing: id 1 | task 51 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.73 s / 21.83 tokens per second 1.29.286.385 I slot print_timing: id 2 | task 50 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.73 s / 18.86 tokens per second 1.29.297.785 I slot print_timing: id 3 | task 52 | prompt processing, n_tokens = 132, progress = 0.97, t = 5.73 s / 23.05 tokens per second 1.29.875.667 I slot print_timing: id 0 | task 49 | prompt eval time = 6538.83 ms / 102 tokens ( 64.11 ms per token, 15.60 tokens per second) 1.29.875.672 I slot print_timing: id 0 | task 49 | eval time = 210.29 ms / 2 tokens ( 210.29 ms per token, 4.76 tokens per second) 1.29.875.673 I slot print_timing: id 0 | task 49 | total time = 6749.12 ms / 104 tokens 1.29.875.673 I slot print_timing: id 0 | task 49 | graphs reused = 1 1.29.875.674 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.875.693 I slot release: id 0 | task 49 | stop processing: n_tokens = 103, truncated = 0 1.29.875.850 I slot print_timing: id 1 | task 51 | prompt eval time = 6538.98 ms / 129 tokens ( 50.69 ms per token, 19.73 tokens per second) 1.29.875.853 I slot print_timing: id 1 | task 51 | eval time = 210.32 ms / 2 tokens ( 210.32 ms per token, 4.75 tokens per second) 1.29.875.854 I slot print_timing: id 1 | task 51 | total time = 6749.29 ms / 131 tokens 1.29.875.854 I slot print_timing: id 1 | task 51 | graphs reused = 1 1.29.875.854 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.875.869 I slot release: id 1 | task 51 | stop processing: n_tokens = 130, truncated = 0 1.29.876.037 I slot print_timing: id 2 | task 50 | prompt eval time = 6539.18 ms / 112 tokens ( 58.39 ms per token, 17.13 tokens per second) 1.29.876.041 I slot print_timing: id 2 | task 50 | eval time = 210.29 ms / 2 tokens ( 210.29 ms per token, 4.76 tokens per second) 1.29.876.042 I slot print_timing: id 2 | task 50 | total time = 6749.47 ms / 114 tokens 1.29.876.042 I slot print_timing: id 2 | task 50 | graphs reused = 1 1.29.876.042 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.876.051 I slot release: id 2 | task 50 | stop processing: n_tokens = 113, truncated = 0 1.29.876.231 I slot print_timing: id 3 | task 52 | prompt eval time = 6539.37 ms / 136 tokens ( 48.08 ms per token, 20.80 tokens per second) 1.29.876.233 I slot print_timing: id 3 | task 52 | eval time = 210.28 ms / 2 tokens ( 210.28 ms per token, 4.76 tokens per second) 1.29.876.234 I slot print_timing: id 3 | task 52 | total time = 6749.65 ms / 138 tokens 1.29.876.234 I slot print_timing: id 3 | task 52 | graphs reused = 1 1.29.876.234 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.876.244 I slot release: id 3 | task 52 | stop processing: n_tokens = 137, truncated = 0 1.29.882.357 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.272 1.29.890.838 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 1.29.890.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 1.29.915.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 1.29.923.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 1.29.945.868 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.215 1.29.945.946 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 1.29.945.984 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.248 1.29.946.021 I slot launch_slot_: id 2 | task 57 | processing task, is_child = 0 1.29.946.042 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.204 1.29.946.080 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 1.37.516.209 I slot print_timing: id 0 | task 56 | prompt processing, n_tokens = 128, progress = 0.97, t = 7.57 s / 16.91 tokens per second 1.37.813.639 I slot print_timing: id 1 | task 58 | prompt processing, n_tokens = 178, progress = 0.98, t = 7.57 s / 23.51 tokens per second 1.37.818.081 I slot print_timing: id 2 | task 57 | prompt processing, n_tokens = 162, progress = 0.98, t = 7.57 s / 21.40 tokens per second 1.37.822.516 I slot print_timing: id 3 | task 59 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.57 s / 22.85 tokens per second 1.38.400.237 I slot print_timing: id 0 | task 56 | prompt eval time = 8244.05 ms / 132 tokens ( 62.45 ms per token, 16.01 tokens per second) 1.38.400.241 I slot print_timing: id 0 | task 56 | eval time = 210.09 ms / 2 tokens ( 210.09 ms per token, 4.76 tokens per second) 1.38.400.242 I slot print_timing: id 0 | task 56 | total time = 8454.14 ms / 134 tokens 1.38.400.242 I slot print_timing: id 0 | task 56 | graphs reused = 1 1.38.400.243 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.400.261 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 1.38.400.414 I slot print_timing: id 1 | task 58 | prompt eval time = 8244.23 ms / 182 tokens ( 45.30 ms per token, 22.08 tokens per second) 1.38.400.417 I slot print_timing: id 1 | task 58 | eval time = 210.07 ms / 2 tokens ( 210.07 ms per token, 4.76 tokens per second) 1.38.400.417 I slot print_timing: id 1 | task 58 | total time = 8454.30 ms / 184 tokens 1.38.400.417 I slot print_timing: id 1 | task 58 | graphs reused = 1 1.38.400.418 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.400.432 I slot release: id 1 | task 58 | stop processing: n_tokens = 183, truncated = 0 1.38.400.599 I slot print_timing: id 2 | task 57 | prompt eval time = 8244.41 ms / 166 tokens ( 49.67 ms per token, 20.13 tokens per second) 1.38.400.600 I slot print_timing: id 2 | task 57 | eval time = 210.05 ms / 2 tokens ( 210.05 ms per token, 4.76 tokens per second) 1.38.400.601 I slot print_timing: id 2 | task 57 | total time = 8454.47 ms / 168 tokens 1.38.400.601 I slot print_timing: id 2 | task 57 | graphs reused = 1 1.38.400.601 I slot print_timing: id 2 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.400.611 I slot release: id 2 | task 57 | stop processing: n_tokens = 167, truncated = 0 1.38.400.798 I slot print_timing: id 3 | task 59 | prompt eval time = 8244.62 ms / 177 tokens ( 46.58 ms per token, 21.47 tokens per second) 1.38.400.800 I slot print_timing: id 3 | task 59 | eval time = 210.04 ms / 2 tokens ( 210.04 ms per token, 4.76 tokens per second) 1.38.400.801 I slot print_timing: id 3 | task 59 | total time = 8454.65 ms / 179 tokens 1.38.400.801 I slot print_timing: id 3 | task 59 | graphs reused = 1 1.38.400.801 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.400.811 I slot release: id 3 | task 59 | stop processing: n_tokens = 178, truncated = 0 1.38.407.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.211 1.38.407.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 1.38.415.731 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 1.38.415.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 1.38.444.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.820 MiB) 1.38.452.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.630 MiB) 1.38.475.157 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.153 1.38.475.250 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 1.38.475.293 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.168 1.38.475.330 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 1.38.475.351 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.157 1.38.478.700 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 1.45.128.574 I slot print_timing: id 0 | task 63 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.65 s / 17.90 tokens per second 1.45.555.303 I slot print_timing: id 1 | task 64 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.65 s / 21.81 tokens per second 1.45.559.720 I slot print_timing: id 2 | task 65 | prompt processing, n_tokens = 165, progress = 0.98, t = 6.65 s / 24.81 tokens per second 1.45.564.168 I slot print_timing: id 3 | task 66 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.65 s / 20.45 tokens per second 1.46.142.131 I slot print_timing: id 0 | task 63 | prompt eval time = 7452.99 ms / 123 tokens ( 60.59 ms per token, 16.50 tokens per second) 1.46.142.135 I slot print_timing: id 0 | task 63 | eval time = 210.43 ms / 2 tokens ( 210.43 ms per token, 4.75 tokens per second) 1.46.142.136 I slot print_timing: id 0 | task 63 | total time = 7663.42 ms / 125 tokens 1.46.142.136 I slot print_timing: id 0 | task 63 | graphs reused = 1 1.46.142.136 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.142.155 I slot release: id 0 | task 63 | stop processing: n_tokens = 124, truncated = 0 1.46.142.307 I slot print_timing: id 1 | task 64 | prompt eval time = 7453.18 ms / 149 tokens ( 50.02 ms per token, 19.99 tokens per second) 1.46.142.309 I slot print_timing: id 1 | task 64 | eval time = 210.39 ms / 2 tokens ( 210.39 ms per token, 4.75 tokens per second) 1.46.142.309 I slot print_timing: id 1 | task 64 | total time = 7663.58 ms / 151 tokens 1.46.142.310 I slot print_timing: id 1 | task 64 | graphs reused = 1 1.46.142.310 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.142.325 I slot release: id 1 | task 64 | stop processing: n_tokens = 150, truncated = 0 1.46.142.503 I slot print_timing: id 2 | task 65 | prompt eval time = 7453.36 ms / 169 tokens ( 44.10 ms per token, 22.67 tokens per second) 1.46.142.505 I slot print_timing: id 2 | task 65 | eval time = 210.39 ms / 2 tokens ( 210.39 ms per token, 4.75 tokens per second) 1.46.142.505 I slot print_timing: id 2 | task 65 | total time = 7663.75 ms / 171 tokens 1.46.142.505 I slot print_timing: id 2 | task 65 | graphs reused = 1 1.46.142.506 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.142.524 I slot release: id 2 | task 65 | stop processing: n_tokens = 170, truncated = 0 1.46.142.692 I slot print_timing: id 3 | task 66 | prompt eval time = 7453.57 ms / 140 tokens ( 53.24 ms per token, 18.78 tokens per second) 1.46.142.695 I slot print_timing: id 3 | task 66 | eval time = 210.36 ms / 2 tokens ( 210.36 ms per token, 4.75 tokens per second) 1.46.142.695 I slot print_timing: id 3 | task 66 | total time = 7663.93 ms / 142 tokens 1.46.142.695 I slot print_timing: id 3 | task 66 | graphs reused = 1 1.46.142.696 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.142.704 I slot release: id 3 | task 66 | stop processing: n_tokens = 141, truncated = 0 1.46.148.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.46.156.611 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 1.46.156.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 1.46.165.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 1.46.194.116 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 1.46.202.019 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 1.46.202.088 I slot launch_slot_: id 3 | task 70 | processing task, is_child = 0 1.46.202.129 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.187 1.46.202.164 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 1.46.202.186 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.165 1.46.202.219 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 1.53.212.739 I slot print_timing: id 0 | task 71 | prompt processing, n_tokens = 124, progress = 0.97, t = 7.01 s / 17.69 tokens per second 1.53.382.301 I slot print_timing: id 1 | task 72 | prompt processing, n_tokens = 159, progress = 0.98, t = 7.01 s / 22.68 tokens per second 1.53.386.940 I slot print_timing: id 2 | task 73 | prompt processing, n_tokens = 157, progress = 0.98, t = 7.01 s / 22.40 tokens per second 1.53.391.850 I slot print_timing: id 3 | task 70 | prompt processing, n_tokens = 107, progress = 0.96, t = 7.01 s / 15.26 tokens per second 1.53.970.189 I slot print_timing: id 0 | task 71 | prompt eval time = 7557.66 ms / 128 tokens ( 59.04 ms per token, 16.94 tokens per second) 1.53.970.194 I slot print_timing: id 0 | task 71 | eval time = 210.30 ms / 2 tokens ( 210.30 ms per token, 4.76 tokens per second) 1.53.970.195 I slot print_timing: id 0 | task 71 | total time = 7767.96 ms / 130 tokens 1.53.970.195 I slot print_timing: id 0 | task 71 | graphs reused = 1 1.53.970.196 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.970.222 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 1.53.970.372 I slot print_timing: id 1 | task 72 | prompt eval time = 7557.81 ms / 163 tokens ( 46.37 ms per token, 21.57 tokens per second) 1.53.970.377 I slot print_timing: id 1 | task 72 | eval time = 210.32 ms / 2 tokens ( 210.32 ms per token, 4.75 tokens per second) 1.53.970.377 I slot print_timing: id 1 | task 72 | total time = 7768.13 ms / 165 tokens 1.53.970.378 I slot print_timing: id 1 | task 72 | graphs reused = 1 1.53.970.378 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.970.392 I slot release: id 1 | task 72 | stop processing: n_tokens = 164, truncated = 0 1.53.970.558 I slot print_timing: id 2 | task 73 | prompt eval time = 7558.02 ms / 161 tokens ( 46.94 ms per token, 21.30 tokens per second) 1.53.970.562 I slot print_timing: id 2 | task 73 | eval time = 210.29 ms / 2 tokens ( 210.29 ms per token, 4.76 tokens per second) 1.53.970.563 I slot print_timing: id 2 | task 73 | total time = 7768.31 ms / 163 tokens 1.53.970.563 I slot print_timing: id 2 | task 73 | graphs reused = 1 1.53.970.563 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.970.573 I slot release: id 2 | task 73 | stop processing: n_tokens = 162, truncated = 0 1.53.970.748 I slot print_timing: id 3 | task 70 | prompt eval time = 7558.20 ms / 111 tokens ( 68.09 ms per token, 14.69 tokens per second) 1.53.970.749 I slot print_timing: id 3 | task 70 | eval time = 210.28 ms / 2 tokens ( 210.28 ms per token, 4.76 tokens per second) 1.53.970.750 I slot print_timing: id 3 | task 70 | total time = 7768.48 ms / 113 tokens 1.53.970.750 I slot print_timing: id 3 | task 70 | graphs reused = 1 1.53.970.750 I slot print_timing: id 3 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.970.757 I slot release: id 3 | task 70 | stop processing: n_tokens = 112, truncated = 0 1.53.976.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 1.53.976.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 1.53.985.417 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 1.53.985.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 1.54.013.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.755 MiB) 1.54.036.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.632 MiB) 1.54.048.269 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.177 1.54.048.365 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 1.54.048.407 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.173 1.54.048.444 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 1.54.048.470 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.250 1.54.048.513 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 2.00.733.489 I slot print_timing: id 0 | task 78 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.68 s / 16.16 tokens per second 2.00.907.467 I slot print_timing: id 1 | task 77 | prompt processing, n_tokens = 105, progress = 0.96, t = 6.68 s / 15.71 tokens per second 2.00.911.848 I slot print_timing: id 2 | task 79 | prompt processing, n_tokens = 163, progress = 0.98, t = 6.68 s / 24.38 tokens per second 2.00.916.300 I slot print_timing: id 3 | task 80 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.68 s / 23.93 tokens per second 2.01.494.001 I slot print_timing: id 0 | task 78 | prompt eval time = 7235.03 ms / 112 tokens ( 64.60 ms per token, 15.48 tokens per second) 2.01.494.003 I slot print_timing: id 0 | task 78 | eval time = 210.45 ms / 2 tokens ( 210.45 ms per token, 4.75 tokens per second) 2.01.494.003 I slot print_timing: id 0 | task 78 | total time = 7445.48 ms / 114 tokens 2.01.494.004 I slot print_timing: id 0 | task 78 | graphs reused = 1 2.01.494.004 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.494.023 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 2.01.494.173 I slot print_timing: id 1 | task 77 | prompt eval time = 7235.21 ms / 109 tokens ( 66.38 ms per token, 15.07 tokens per second) 2.01.494.178 I slot print_timing: id 1 | task 77 | eval time = 210.42 ms / 2 tokens ( 210.42 ms per token, 4.75 tokens per second) 2.01.494.178 I slot print_timing: id 1 | task 77 | total time = 7445.63 ms / 111 tokens 2.01.494.178 I slot print_timing: id 1 | task 77 | graphs reused = 1 2.01.494.179 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.494.196 I slot release: id 1 | task 77 | stop processing: n_tokens = 110, truncated = 0 2.01.494.370 I slot print_timing: id 2 | task 79 | prompt eval time = 7235.40 ms / 167 tokens ( 43.33 ms per token, 23.08 tokens per second) 2.01.494.377 I slot print_timing: id 2 | task 79 | eval time = 210.42 ms / 2 tokens ( 210.42 ms per token, 4.75 tokens per second) 2.01.494.377 I slot print_timing: id 2 | task 79 | total time = 7445.82 ms / 169 tokens 2.01.494.378 I slot print_timing: id 2 | task 79 | graphs reused = 1 2.01.494.378 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.494.392 I slot release: id 2 | task 79 | stop processing: n_tokens = 168, truncated = 0 2.01.494.554 I slot print_timing: id 3 | task 80 | prompt eval time = 7235.60 ms / 164 tokens ( 44.12 ms per token, 22.67 tokens per second) 2.01.494.555 I slot print_timing: id 3 | task 80 | eval time = 210.38 ms / 2 tokens ( 210.38 ms per token, 4.75 tokens per second) 2.01.494.556 I slot print_timing: id 3 | task 80 | total time = 7445.98 ms / 166 tokens 2.01.494.556 I slot print_timing: id 3 | task 80 | graphs reused = 1 2.01.494.556 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.494.566 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 2.01.500.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.248 2.01.500.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 2.01.508.649 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 2.01.508.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.01.516.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 2.01.526.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.444 MiB) 2.01.537.354 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 2.01.540.714 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 2.01.540.755 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.167 2.01.540.788 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 2.01.540.806 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.170 2.01.540.837 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 2.07.576.243 I slot print_timing: id 0 | task 84 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.04 s / 19.22 tokens per second 2.07.887.295 I slot print_timing: id 1 | task 85 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.04 s / 19.55 tokens per second 2.07.892.352 I slot print_timing: id 2 | task 86 | prompt processing, n_tokens = 143, progress = 0.97, t = 6.04 s / 23.69 tokens per second 2.07.897.216 I slot print_timing: id 3 | task 87 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.04 s / 21.04 tokens per second 2.08.474.465 I slot print_timing: id 0 | task 84 | prompt eval time = 6723.35 ms / 120 tokens ( 56.03 ms per token, 17.85 tokens per second) 2.08.474.467 I slot print_timing: id 0 | task 84 | eval time = 210.27 ms / 2 tokens ( 210.27 ms per token, 4.76 tokens per second) 2.08.474.467 I slot print_timing: id 0 | task 84 | total time = 6933.62 ms / 122 tokens 2.08.474.468 I slot print_timing: id 0 | task 84 | graphs reused = 1 2.08.474.468 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.474.490 I slot release: id 0 | task 84 | stop processing: n_tokens = 121, truncated = 0 2.08.474.641 I slot print_timing: id 1 | task 85 | prompt eval time = 6723.52 ms / 122 tokens ( 55.11 ms per token, 18.15 tokens per second) 2.08.474.644 I slot print_timing: id 1 | task 85 | eval time = 210.27 ms / 2 tokens ( 210.27 ms per token, 4.76 tokens per second) 2.08.474.644 I slot print_timing: id 1 | task 85 | total time = 6933.78 ms / 124 tokens 2.08.474.644 I slot print_timing: id 1 | task 85 | graphs reused = 1 2.08.474.645 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.474.657 I slot release: id 1 | task 85 | stop processing: n_tokens = 123, truncated = 0 2.08.474.828 I slot print_timing: id 2 | task 86 | prompt eval time = 6723.71 ms / 147 tokens ( 45.74 ms per token, 21.86 tokens per second) 2.08.474.834 I slot print_timing: id 2 | task 86 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 2.08.474.834 I slot print_timing: id 2 | task 86 | total time = 6933.96 ms / 149 tokens 2.08.474.835 I slot print_timing: id 2 | task 86 | graphs reused = 1 2.08.474.835 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.474.845 I slot release: id 2 | task 86 | stop processing: n_tokens = 148, truncated = 0 2.08.475.026 I slot print_timing: id 3 | task 87 | prompt eval time = 6723.89 ms / 131 tokens ( 51.33 ms per token, 19.48 tokens per second) 2.08.475.032 I slot print_timing: id 3 | task 87 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 2.08.475.032 I slot print_timing: id 3 | task 87 | total time = 6934.13 ms / 133 tokens 2.08.475.032 I slot print_timing: id 3 | task 87 | graphs reused = 1 2.08.475.033 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.475.041 I slot release: id 3 | task 87 | stop processing: n_tokens = 132, truncated = 0 2.08.481.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.231 2.08.489.806 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 2.08.489.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 2.08.499.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.380 MiB) 2.08.527.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 2.08.539.377 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.228 2.08.542.812 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 2.08.542.853 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.189 2.08.542.894 I slot launch_slot_: id 2 | task 92 | processing task, is_child = 0 2.08.542.914 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 2.08.542.952 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 2.14.623.340 I slot print_timing: id 0 | task 91 | prompt processing, n_tokens = 120, progress = 0.97, t = 6.08 s / 19.74 tokens per second 2.14.925.959 I slot print_timing: id 1 | task 93 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.08 s / 22.53 tokens per second 2.14.930.416 I slot print_timing: id 2 | task 92 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.08 s / 20.89 tokens per second 2.14.934.813 I slot print_timing: id 3 | task 94 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.08 s / 23.03 tokens per second 2.15.512.548 I slot print_timing: id 0 | task 91 | prompt eval time = 6759.10 ms / 124 tokens ( 54.51 ms per token, 18.35 tokens per second) 2.15.512.551 I slot print_timing: id 0 | task 91 | eval time = 210.49 ms / 2 tokens ( 210.49 ms per token, 4.75 tokens per second) 2.15.512.552 I slot print_timing: id 0 | task 91 | total time = 6969.59 ms / 126 tokens 2.15.512.552 I slot print_timing: id 0 | task 91 | graphs reused = 1 2.15.512.552 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.512.574 I slot release: id 0 | task 91 | stop processing: n_tokens = 125, truncated = 0 2.15.512.722 I slot print_timing: id 1 | task 93 | prompt eval time = 6759.29 ms / 141 tokens ( 47.94 ms per token, 20.86 tokens per second) 2.15.512.724 I slot print_timing: id 1 | task 93 | eval time = 210.44 ms / 2 tokens ( 210.44 ms per token, 4.75 tokens per second) 2.15.512.724 I slot print_timing: id 1 | task 93 | total time = 6969.73 ms / 143 tokens 2.15.512.724 I slot print_timing: id 1 | task 93 | graphs reused = 1 2.15.512.725 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.512.735 I slot release: id 1 | task 93 | stop processing: n_tokens = 142, truncated = 0 2.15.512.903 I slot print_timing: id 2 | task 92 | prompt eval time = 6759.50 ms / 131 tokens ( 51.60 ms per token, 19.38 tokens per second) 2.15.512.906 I slot print_timing: id 2 | task 92 | eval time = 210.40 ms / 2 tokens ( 210.40 ms per token, 4.75 tokens per second) 2.15.512.906 I slot print_timing: id 2 | task 92 | total time = 6969.90 ms / 133 tokens 2.15.512.906 I slot print_timing: id 2 | task 92 | graphs reused = 1 2.15.512.906 I slot print_timing: id 2 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.512.915 I slot release: id 2 | task 92 | stop processing: n_tokens = 132, truncated = 0 2.15.513.081 I slot print_timing: id 3 | task 94 | prompt eval time = 6759.69 ms / 144 tokens ( 46.94 ms per token, 21.30 tokens per second) 2.15.513.082 I slot print_timing: id 3 | task 94 | eval time = 210.35 ms / 2 tokens ( 210.35 ms per token, 4.75 tokens per second) 2.15.513.083 I slot print_timing: id 3 | task 94 | total time = 6970.05 ms / 146 tokens 2.15.513.083 I slot print_timing: id 3 | task 94 | graphs reused = 1 2.15.513.083 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.513.090 I slot release: id 3 | task 94 | stop processing: n_tokens = 145, truncated = 0 2.15.519.281 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 2.15.528.057 I slot launch_slot_: id 2 | task 98 | processing task, is_child = 0 2.15.528.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.15.541.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.15.554.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 2.15.572.602 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 2.15.572.653 I slot launch_slot_: id 3 | task 99 | processing task, is_child = 0 2.15.572.693 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 2.15.572.728 I slot launch_slot_: id 0 | task 100 | processing task, is_child = 0 2.15.572.747 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 2.15.572.779 I slot launch_slot_: id 1 | task 101 | processing task, is_child = 0 2.21.516.351 I slot print_timing: id 0 | task 100 | prompt processing, n_tokens = 117, progress = 0.97, t = 5.94 s / 19.69 tokens per second 2.21.813.679 I slot print_timing: id 1 | task 101 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.94 s / 28.27 tokens per second 2.21.818.510 I slot print_timing: id 2 | task 98 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.94 s / 17.33 tokens per second 2.21.823.395 I slot print_timing: id 3 | task 99 | prompt processing, n_tokens = 114, progress = 0.97, t = 5.94 s / 19.18 tokens per second 2.22.401.449 I slot print_timing: id 0 | task 100 | prompt eval time = 6618.56 ms / 121 tokens ( 54.70 ms per token, 18.28 tokens per second) 2.22.401.451 I slot print_timing: id 0 | task 100 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 2.22.401.452 I slot print_timing: id 0 | task 100 | total time = 6828.66 ms / 123 tokens 2.22.401.452 I slot print_timing: id 0 | task 100 | graphs reused = 1 2.22.401.453 I slot print_timing: id 0 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.401.482 I slot release: id 0 | task 100 | stop processing: n_tokens = 122, truncated = 0 2.22.401.633 I slot print_timing: id 1 | task 101 | prompt eval time = 6618.72 ms / 172 tokens ( 38.48 ms per token, 25.99 tokens per second) 2.22.401.638 I slot print_timing: id 1 | task 101 | eval time = 210.11 ms / 2 tokens ( 210.11 ms per token, 4.76 tokens per second) 2.22.401.638 I slot print_timing: id 1 | task 101 | total time = 6828.83 ms / 174 tokens 2.22.401.639 I slot print_timing: id 1 | task 101 | graphs reused = 1 2.22.401.639 I slot print_timing: id 1 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.401.652 I slot release: id 1 | task 101 | stop processing: n_tokens = 173, truncated = 0 2.22.401.828 I slot print_timing: id 2 | task 98 | prompt eval time = 6618.94 ms / 107 tokens ( 61.86 ms per token, 16.17 tokens per second) 2.22.401.830 I slot print_timing: id 2 | task 98 | eval time = 210.07 ms / 2 tokens ( 210.07 ms per token, 4.76 tokens per second) 2.22.401.830 I slot print_timing: id 2 | task 98 | total time = 6829.01 ms / 109 tokens 2.22.401.830 I slot print_timing: id 2 | task 98 | graphs reused = 1 2.22.401.831 I slot print_timing: id 2 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.401.851 I slot release: id 2 | task 98 | stop processing: n_tokens = 108, truncated = 0 2.22.402.020 I slot print_timing: id 3 | task 99 | prompt eval time = 6619.15 ms / 118 tokens ( 56.09 ms per token, 17.83 tokens per second) 2.22.402.021 I slot print_timing: id 3 | task 99 | eval time = 210.04 ms / 2 tokens ( 210.04 ms per token, 4.76 tokens per second) 2.22.402.022 I slot print_timing: id 3 | task 99 | total time = 6829.19 ms / 120 tokens 2.22.402.022 I slot print_timing: id 3 | task 99 | graphs reused = 1 2.22.402.022 I slot print_timing: id 3 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.402.030 I slot release: id 3 | task 99 | stop processing: n_tokens = 119, truncated = 0 2.22.407.985 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.269 2.22.408.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.130 MiB) 2.22.422.632 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 2.22.422.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.693 MiB) 2.22.434.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 2.22.462.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 2.22.469.990 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.244 2.22.470.061 I slot launch_slot_: id 3 | task 105 | processing task, is_child = 0 2.22.470.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.230 2.22.470.140 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 2.22.470.162 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 2.22.470.206 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 2.29.740.171 I slot print_timing: id 0 | task 107 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.27 s / 23.80 tokens per second 2.30.167.792 I slot print_timing: id 1 | task 108 | prompt processing, n_tokens = 236, progress = 0.98, t = 7.27 s / 32.46 tokens per second 2.30.172.256 I slot print_timing: id 2 | task 106 | prompt processing, n_tokens = 112, progress = 0.97, t = 7.27 s / 15.41 tokens per second 2.30.176.740 I slot print_timing: id 3 | task 105 | prompt processing, n_tokens = 132, progress = 0.97, t = 7.27 s / 18.16 tokens per second 2.30.754.961 I slot print_timing: id 0 | task 107 | prompt eval time = 8074.21 ms / 177 tokens ( 45.62 ms per token, 21.92 tokens per second) 2.30.754.963 I slot print_timing: id 0 | task 107 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 2.30.754.964 I slot print_timing: id 0 | task 107 | total time = 8284.75 ms / 179 tokens 2.30.754.964 I slot print_timing: id 0 | task 107 | graphs reused = 1 2.30.754.965 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.754.987 I slot release: id 0 | task 107 | stop processing: n_tokens = 178, truncated = 0 2.30.755.136 I slot print_timing: id 1 | task 108 | prompt eval time = 8074.39 ms / 240 tokens ( 33.64 ms per token, 29.72 tokens per second) 2.30.755.138 I slot print_timing: id 1 | task 108 | eval time = 210.51 ms / 2 tokens ( 210.51 ms per token, 4.75 tokens per second) 2.30.755.138 I slot print_timing: id 1 | task 108 | total time = 8284.90 ms / 242 tokens 2.30.755.138 I slot print_timing: id 1 | task 108 | graphs reused = 1 2.30.755.139 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.755.153 I slot release: id 1 | task 108 | stop processing: n_tokens = 241, truncated = 0 2.30.755.317 I slot print_timing: id 2 | task 106 | prompt eval time = 8074.58 ms / 116 tokens ( 69.61 ms per token, 14.37 tokens per second) 2.30.755.322 I slot print_timing: id 2 | task 106 | eval time = 210.49 ms / 2 tokens ( 210.49 ms per token, 4.75 tokens per second) 2.30.755.323 I slot print_timing: id 2 | task 106 | total time = 8285.07 ms / 118 tokens 2.30.755.323 I slot print_timing: id 2 | task 106 | graphs reused = 1 2.30.755.323 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.755.333 I slot release: id 2 | task 106 | stop processing: n_tokens = 117, truncated = 0 2.30.755.514 I slot print_timing: id 3 | task 105 | prompt eval time = 8074.77 ms / 136 tokens ( 59.37 ms per token, 16.84 tokens per second) 2.30.755.516 I slot print_timing: id 3 | task 105 | eval time = 210.48 ms / 2 tokens ( 210.48 ms per token, 4.75 tokens per second) 2.30.755.516 I slot print_timing: id 3 | task 105 | total time = 8285.26 ms / 138 tokens 2.30.755.517 I slot print_timing: id 3 | task 105 | graphs reused = 1 2.30.755.517 I slot print_timing: id 3 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.755.525 I slot release: id 3 | task 105 | stop processing: n_tokens = 137, truncated = 0 2.30.761.944 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.157 2.30.761.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.568 MiB) 2.30.787.250 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 2.30.787.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 2.30.809.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 2.30.817.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 2.30.825.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 2.30.825.758 I slot launch_slot_: id 2 | task 112 | processing task, is_child = 0 2.30.825.799 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 2.30.829.117 I slot launch_slot_: id 3 | task 114 | processing task, is_child = 0 2.30.829.157 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 2.30.829.195 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 2.39.268.829 I slot print_timing: id 0 | task 113 | prompt processing, n_tokens = 156, progress = 0.97, t = 8.44 s / 18.48 tokens per second 2.39.570.331 I slot print_timing: id 1 | task 115 | prompt processing, n_tokens = 222, progress = 0.98, t = 8.44 s / 26.30 tokens per second 2.39.574.765 I slot print_timing: id 2 | task 112 | prompt processing, n_tokens = 138, progress = 0.97, t = 8.44 s / 16.35 tokens per second 2.39.579.171 I slot print_timing: id 3 | task 114 | prompt processing, n_tokens = 151, progress = 0.97, t = 8.44 s / 17.89 tokens per second 2.40.156.990 I slot print_timing: id 0 | task 113 | prompt eval time = 9117.45 ms / 160 tokens ( 56.98 ms per token, 17.55 tokens per second) 2.40.156.992 I slot print_timing: id 0 | task 113 | eval time = 210.33 ms / 2 tokens ( 210.33 ms per token, 4.75 tokens per second) 2.40.156.992 I slot print_timing: id 0 | task 113 | total time = 9327.78 ms / 162 tokens 2.40.156.993 I slot print_timing: id 0 | task 113 | graphs reused = 1 2.40.156.993 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.157.017 I slot release: id 0 | task 113 | stop processing: n_tokens = 161, truncated = 0 2.40.157.166 I slot print_timing: id 1 | task 115 | prompt eval time = 9117.64 ms / 226 tokens ( 40.34 ms per token, 24.79 tokens per second) 2.40.157.168 I slot print_timing: id 1 | task 115 | eval time = 210.30 ms / 2 tokens ( 210.30 ms per token, 4.76 tokens per second) 2.40.157.168 I slot print_timing: id 1 | task 115 | total time = 9327.94 ms / 228 tokens 2.40.157.168 I slot print_timing: id 1 | task 115 | graphs reused = 1 2.40.157.169 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.157.189 I slot release: id 1 | task 115 | stop processing: n_tokens = 227, truncated = 0 2.40.157.353 I slot print_timing: id 2 | task 112 | prompt eval time = 9117.82 ms / 142 tokens ( 64.21 ms per token, 15.57 tokens per second) 2.40.157.355 I slot print_timing: id 2 | task 112 | eval time = 210.29 ms / 2 tokens ( 210.29 ms per token, 4.76 tokens per second) 2.40.157.355 I slot print_timing: id 2 | task 112 | total time = 9328.11 ms / 144 tokens 2.40.157.355 I slot print_timing: id 2 | task 112 | graphs reused = 1 2.40.157.355 I slot print_timing: id 2 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.157.364 I slot release: id 2 | task 112 | stop processing: n_tokens = 143, truncated = 0 2.40.157.522 I slot print_timing: id 3 | task 114 | prompt eval time = 9118.02 ms / 155 tokens ( 58.83 ms per token, 17.00 tokens per second) 2.40.157.526 I slot print_timing: id 3 | task 114 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 2.40.157.526 I slot print_timing: id 3 | task 114 | total time = 9328.26 ms / 157 tokens 2.40.157.527 I slot print_timing: id 3 | task 114 | graphs reused = 1 2.40.157.527 I slot print_timing: id 3 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.157.536 I slot release: id 3 | task 114 | stop processing: n_tokens = 156, truncated = 0 2.40.163.494 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 2.40.173.444 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 2.40.173.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.40.181.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 2.40.209.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.882 MiB) 2.40.218.113 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 2.40.218.208 I slot launch_slot_: id 3 | task 120 | processing task, is_child = 0 2.40.218.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 2.40.218.301 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 2.40.218.331 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 2.40.221.801 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 2.46.862.335 I slot print_timing: id 0 | task 121 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.64 s / 20.63 tokens per second 2.47.156.620 I slot print_timing: id 1 | task 122 | prompt processing, n_tokens = 188, progress = 0.98, t = 6.64 s / 28.31 tokens per second 2.47.161.083 I slot print_timing: id 2 | task 119 | prompt processing, n_tokens = 101, progress = 0.96, t = 6.64 s / 15.21 tokens per second 2.47.165.971 I slot print_timing: id 3 | task 120 | prompt processing, n_tokens = 110, progress = 0.96, t = 6.64 s / 16.57 tokens per second 2.47.743.795 I slot print_timing: id 0 | task 121 | prompt eval time = 7311.77 ms / 141 tokens ( 51.86 ms per token, 19.28 tokens per second) 2.47.743.800 I slot print_timing: id 0 | task 121 | eval time = 210.21 ms / 2 tokens ( 210.21 ms per token, 4.76 tokens per second) 2.47.743.801 I slot print_timing: id 0 | task 121 | total time = 7521.98 ms / 143 tokens 2.47.743.801 I slot print_timing: id 0 | task 121 | graphs reused = 1 2.47.743.802 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.743.823 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 2.47.743.975 I slot print_timing: id 1 | task 122 | prompt eval time = 7311.93 ms / 192 tokens ( 38.08 ms per token, 26.26 tokens per second) 2.47.743.978 I slot print_timing: id 1 | task 122 | eval time = 210.21 ms / 2 tokens ( 210.21 ms per token, 4.76 tokens per second) 2.47.743.979 I slot print_timing: id 1 | task 122 | total time = 7522.14 ms / 194 tokens 2.47.743.979 I slot print_timing: id 1 | task 122 | graphs reused = 1 2.47.743.979 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.743.992 I slot release: id 1 | task 122 | stop processing: n_tokens = 193, truncated = 0 2.47.744.163 I slot print_timing: id 2 | task 119 | prompt eval time = 7312.12 ms / 105 tokens ( 69.64 ms per token, 14.36 tokens per second) 2.47.744.165 I slot print_timing: id 2 | task 119 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 2.47.744.165 I slot print_timing: id 2 | task 119 | total time = 7522.32 ms / 107 tokens 2.47.744.165 I slot print_timing: id 2 | task 119 | graphs reused = 1 2.47.744.166 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.744.174 I slot release: id 2 | task 119 | stop processing: n_tokens = 106, truncated = 0 2.47.744.332 I slot print_timing: id 3 | task 120 | prompt eval time = 7312.32 ms / 114 tokens ( 64.14 ms per token, 15.59 tokens per second) 2.47.744.335 I slot print_timing: id 3 | task 120 | eval time = 210.15 ms / 2 tokens ( 210.15 ms per token, 4.76 tokens per second) 2.47.744.335 I slot print_timing: id 3 | task 120 | total time = 7522.47 ms / 116 tokens 2.47.744.335 I slot print_timing: id 3 | task 120 | graphs reused = 1 2.47.744.336 I slot print_timing: id 3 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.744.345 I slot release: id 3 | task 120 | stop processing: n_tokens = 115, truncated = 0 2.47.750.510 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 2.47.759.016 I slot launch_slot_: id 2 | task 127 | processing task, is_child = 0 2.47.759.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 2.47.766.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 2.47.774.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.506 MiB) 2.47.782.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 2.47.782.626 I slot launch_slot_: id 0 | task 128 | processing task, is_child = 0 2.47.782.665 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 2.47.782.702 I slot launch_slot_: id 3 | task 126 | processing task, is_child = 0 2.47.782.725 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 2.47.782.764 I slot launch_slot_: id 1 | task 129 | processing task, is_child = 0 2.53.681.169 I slot print_timing: id 0 | task 128 | prompt processing, n_tokens = 131, progress = 0.97, t = 5.90 s / 22.21 tokens per second 2.54.439.374 I slot print_timing: id 1 | task 129 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.90 s / 28.48 tokens per second 2.54.443.814 I slot print_timing: id 2 | task 127 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.90 s / 20.01 tokens per second 2.54.448.271 I slot print_timing: id 3 | task 126 | prompt processing, n_tokens = 104, progress = 0.96, t = 5.90 s / 17.63 tokens per second 2.55.025.742 I slot print_timing: id 0 | task 128 | prompt eval time = 7032.82 ms / 135 tokens ( 52.09 ms per token, 19.20 tokens per second) 2.55.025.744 I slot print_timing: id 0 | task 128 | eval time = 210.15 ms / 2 tokens ( 210.15 ms per token, 4.76 tokens per second) 2.55.025.745 I slot print_timing: id 0 | task 128 | total time = 7242.97 ms / 137 tokens 2.55.025.745 I slot print_timing: id 0 | task 128 | graphs reused = 1 2.55.025.746 I slot print_timing: id 0 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.025.765 I slot release: id 0 | task 128 | stop processing: n_tokens = 136, truncated = 0 2.55.025.913 I slot print_timing: id 1 | task 129 | prompt eval time = 7033.01 ms / 172 tokens ( 40.89 ms per token, 24.46 tokens per second) 2.55.025.916 I slot print_timing: id 1 | task 129 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 2.55.025.917 I slot print_timing: id 1 | task 129 | total time = 7243.12 ms / 174 tokens 2.55.025.917 I slot print_timing: id 1 | task 129 | graphs reused = 1 2.55.025.917 I slot print_timing: id 1 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.025.930 I slot release: id 1 | task 129 | stop processing: n_tokens = 173, truncated = 0 2.55.026.095 I slot print_timing: id 2 | task 127 | prompt eval time = 7033.19 ms / 122 tokens ( 57.65 ms per token, 17.35 tokens per second) 2.55.026.097 I slot print_timing: id 2 | task 127 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 2.55.026.097 I slot print_timing: id 2 | task 127 | total time = 7243.29 ms / 124 tokens 2.55.026.097 I slot print_timing: id 2 | task 127 | graphs reused = 1 2.55.026.098 I slot print_timing: id 2 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.026.107 I slot release: id 2 | task 127 | stop processing: n_tokens = 123, truncated = 0 2.55.026.276 I slot print_timing: id 3 | task 126 | prompt eval time = 7033.38 ms / 108 tokens ( 65.12 ms per token, 15.36 tokens per second) 2.55.026.278 I slot print_timing: id 3 | task 126 | eval time = 210.08 ms / 2 tokens ( 210.08 ms per token, 4.76 tokens per second) 2.55.026.278 I slot print_timing: id 3 | task 126 | total time = 7243.46 ms / 110 tokens 2.55.026.279 I slot print_timing: id 3 | task 126 | graphs reused = 1 2.55.026.279 I slot print_timing: id 3 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.026.286 I slot release: id 3 | task 126 | stop processing: n_tokens = 109, truncated = 0 2.55.032.573 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.206 2.55.032.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 2.55.041.173 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 2.55.041.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.756 MiB) 2.55.049.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 2.55.057.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 2.55.064.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 2.55.068.340 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 2.55.068.388 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.162 2.55.068.428 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 2.55.068.448 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.257 2.55.068.487 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 3.01.005.530 I slot print_timing: id 0 | task 134 | prompt processing, n_tokens = 130, progress = 0.97, t = 5.94 s / 21.90 tokens per second 3.01.765.527 I slot print_timing: id 1 | task 135 | prompt processing, n_tokens = 131, progress = 0.97, t = 5.94 s / 22.06 tokens per second 3.01.770.324 I slot print_timing: id 2 | task 133 | prompt processing, n_tokens = 116, progress = 0.97, t = 5.94 s / 19.54 tokens per second 3.01.775.342 I slot print_timing: id 3 | task 136 | prompt processing, n_tokens = 155, progress = 0.97, t = 5.94 s / 26.11 tokens per second 3.02.353.265 I slot print_timing: id 0 | task 134 | prompt eval time = 7075.10 ms / 134 tokens ( 52.80 ms per token, 18.94 tokens per second) 3.02.353.267 I slot print_timing: id 0 | task 134 | eval time = 209.67 ms / 2 tokens ( 209.67 ms per token, 4.77 tokens per second) 3.02.353.267 I slot print_timing: id 0 | task 134 | total time = 7284.77 ms / 136 tokens 3.02.353.268 I slot print_timing: id 0 | task 134 | graphs reused = 1 3.02.353.268 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.353.292 I slot release: id 0 | task 134 | stop processing: n_tokens = 135, truncated = 0 3.02.353.442 I slot print_timing: id 1 | task 135 | prompt eval time = 7075.26 ms / 135 tokens ( 52.41 ms per token, 19.08 tokens per second) 3.02.353.444 I slot print_timing: id 1 | task 135 | eval time = 209.67 ms / 2 tokens ( 209.67 ms per token, 4.77 tokens per second) 3.02.353.444 I slot print_timing: id 1 | task 135 | total time = 7284.93 ms / 137 tokens 3.02.353.445 I slot print_timing: id 1 | task 135 | graphs reused = 1 3.02.353.445 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.353.456 I slot release: id 1 | task 135 | stop processing: n_tokens = 136, truncated = 0 3.02.353.640 I slot print_timing: id 2 | task 133 | prompt eval time = 7075.45 ms / 120 tokens ( 58.96 ms per token, 16.96 tokens per second) 3.02.353.643 I slot print_timing: id 2 | task 133 | eval time = 209.66 ms / 2 tokens ( 209.66 ms per token, 4.77 tokens per second) 3.02.353.643 I slot print_timing: id 2 | task 133 | total time = 7285.11 ms / 122 tokens 3.02.353.643 I slot print_timing: id 2 | task 133 | graphs reused = 1 3.02.353.644 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.353.652 I slot release: id 2 | task 133 | stop processing: n_tokens = 121, truncated = 0 3.02.353.827 I slot print_timing: id 3 | task 136 | prompt eval time = 7075.65 ms / 159 tokens ( 44.50 ms per token, 22.47 tokens per second) 3.02.353.829 I slot print_timing: id 3 | task 136 | eval time = 209.64 ms / 2 tokens ( 209.64 ms per token, 4.77 tokens per second) 3.02.353.829 I slot print_timing: id 3 | task 136 | total time = 7285.29 ms / 161 tokens 3.02.353.830 I slot print_timing: id 3 | task 136 | graphs reused = 1 3.02.353.830 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.353.840 I slot release: id 3 | task 136 | stop processing: n_tokens = 160, truncated = 0 3.02.359.590 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.207 3.02.367.504 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 3.02.367.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.02.375.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.506 MiB) 3.02.383.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.02.391.962 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.206 3.02.392.023 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 3.02.392.060 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 3.02.392.090 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 3.02.392.109 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.175 3.02.392.151 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 3.09.853.689 I slot print_timing: id 0 | task 140 | prompt processing, n_tokens = 126, progress = 0.97, t = 7.46 s / 16.89 tokens per second 3.10.031.570 I slot print_timing: id 1 | task 141 | prompt processing, n_tokens = 168, progress = 0.98, t = 7.46 s / 22.52 tokens per second 3.10.036.231 I slot print_timing: id 2 | task 142 | prompt processing, n_tokens = 171, progress = 0.98, t = 7.46 s / 22.92 tokens per second 3.10.041.090 I slot print_timing: id 3 | task 143 | prompt processing, n_tokens = 176, progress = 0.98, t = 7.46 s / 23.59 tokens per second 3.10.620.228 I slot print_timing: id 0 | task 140 | prompt eval time = 8016.87 ms / 130 tokens ( 61.67 ms per token, 16.22 tokens per second) 3.10.620.230 I slot print_timing: id 0 | task 140 | eval time = 211.20 ms / 2 tokens ( 211.20 ms per token, 4.73 tokens per second) 3.10.620.230 I slot print_timing: id 0 | task 140 | total time = 8228.06 ms / 132 tokens 3.10.620.231 I slot print_timing: id 0 | task 140 | graphs reused = 1 3.10.620.231 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.620.254 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 3.10.620.407 I slot print_timing: id 1 | task 141 | prompt eval time = 8017.20 ms / 172 tokens ( 46.61 ms per token, 21.45 tokens per second) 3.10.620.410 I slot print_timing: id 1 | task 141 | eval time = 211.03 ms / 2 tokens ( 211.03 ms per token, 4.74 tokens per second) 3.10.620.411 I slot print_timing: id 1 | task 141 | total time = 8228.23 ms / 174 tokens 3.10.620.411 I slot print_timing: id 1 | task 141 | graphs reused = 1 3.10.620.412 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.620.426 I slot release: id 1 | task 141 | stop processing: n_tokens = 173, truncated = 0 3.10.620.588 I slot print_timing: id 2 | task 142 | prompt eval time = 8017.57 ms / 175 tokens ( 45.81 ms per token, 21.83 tokens per second) 3.10.620.590 I slot print_timing: id 2 | task 142 | eval time = 210.84 ms / 2 tokens ( 210.84 ms per token, 4.74 tokens per second) 3.10.620.590 I slot print_timing: id 2 | task 142 | total time = 8228.40 ms / 177 tokens 3.10.620.591 I slot print_timing: id 2 | task 142 | graphs reused = 1 3.10.620.591 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.620.607 I slot release: id 2 | task 142 | stop processing: n_tokens = 176, truncated = 0 3.10.620.761 I slot print_timing: id 3 | task 143 | prompt eval time = 8018.21 ms / 180 tokens ( 44.55 ms per token, 22.45 tokens per second) 3.10.620.762 I slot print_timing: id 3 | task 143 | eval time = 210.35 ms / 2 tokens ( 210.35 ms per token, 4.75 tokens per second) 3.10.620.763 I slot print_timing: id 3 | task 143 | total time = 8228.56 ms / 182 tokens 3.10.620.763 I slot print_timing: id 3 | task 143 | graphs reused = 1 3.10.620.763 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.620.774 I slot release: id 3 | task 143 | stop processing: n_tokens = 181, truncated = 0 3.10.626.101 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 3.10.626.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.10.637.502 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 3.10.645.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 3.10.653.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.10.669.757 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.162 3.10.669.841 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 3.10.669.879 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.159 3.10.669.913 I slot launch_slot_: id 2 | task 148 | processing task, is_child = 0 3.10.669.933 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 3.10.673.264 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 3.15.928.544 I slot print_timing: id 0 | task 147 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.26 s / 22.64 tokens per second 3.16.112.899 I slot print_timing: id 1 | task 149 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.26 s / 21.12 tokens per second 3.16.117.662 I slot print_timing: id 2 | task 148 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.26 s / 22.64 tokens per second 3.16.122.468 I slot print_timing: id 3 | task 150 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.26 s / 21.12 tokens per second 3.16.700.367 I slot print_timing: id 0 | task 147 | prompt eval time = 5816.86 ms / 123 tokens ( 47.29 ms per token, 21.15 tokens per second) 3.16.700.369 I slot print_timing: id 0 | task 147 | eval time = 210.23 ms / 2 tokens ( 210.23 ms per token, 4.76 tokens per second) 3.16.700.369 I slot print_timing: id 0 | task 147 | total time = 6027.09 ms / 125 tokens 3.16.700.370 I slot print_timing: id 0 | task 147 | graphs reused = 1 3.16.700.370 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.700.387 I slot release: id 0 | task 147 | stop processing: n_tokens = 124, truncated = 0 3.16.700.533 I slot print_timing: id 1 | task 149 | prompt eval time = 5817.00 ms / 115 tokens ( 50.58 ms per token, 19.77 tokens per second) 3.16.700.535 I slot print_timing: id 1 | task 149 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 3.16.700.536 I slot print_timing: id 1 | task 149 | total time = 6027.24 ms / 117 tokens 3.16.700.537 I slot print_timing: id 1 | task 149 | graphs reused = 1 3.16.700.537 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.700.549 I slot release: id 1 | task 149 | stop processing: n_tokens = 116, truncated = 0 3.16.700.726 I slot print_timing: id 2 | task 148 | prompt eval time = 5817.17 ms / 123 tokens ( 47.29 ms per token, 21.14 tokens per second) 3.16.700.730 I slot print_timing: id 2 | task 148 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 3.16.700.731 I slot print_timing: id 2 | task 148 | total time = 6027.42 ms / 125 tokens 3.16.700.731 I slot print_timing: id 2 | task 148 | graphs reused = 1 3.16.700.731 I slot print_timing: id 2 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.700.739 I slot release: id 2 | task 148 | stop processing: n_tokens = 124, truncated = 0 3.16.700.918 I slot print_timing: id 3 | task 150 | prompt eval time = 5817.32 ms / 115 tokens ( 50.59 ms per token, 19.77 tokens per second) 3.16.700.919 I slot print_timing: id 3 | task 150 | eval time = 210.28 ms / 2 tokens ( 210.28 ms per token, 4.76 tokens per second) 3.16.700.920 I slot print_timing: id 3 | task 150 | total time = 6027.60 ms / 117 tokens 3.16.700.920 I slot print_timing: id 3 | task 150 | graphs reused = 1 3.16.700.920 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.700.931 I slot release: id 3 | task 150 | stop processing: n_tokens = 116, truncated = 0 3.16.707.068 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 3.16.715.539 I slot launch_slot_: id 3 | task 154 | processing task, is_child = 0 3.16.715.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 3.16.723.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.880 MiB) 3.16.731.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.16.739.400 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 3.16.739.466 I slot launch_slot_: id 0 | task 156 | processing task, is_child = 0 3.16.739.498 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 3.16.739.528 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 3.16.739.551 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 3.16.739.582 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 3.22.839.877 I slot print_timing: id 0 | task 156 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.10 s / 20.33 tokens per second 3.23.136.796 I slot print_timing: id 1 | task 155 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.10 s / 20.65 tokens per second 3.23.141.733 I slot print_timing: id 2 | task 157 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.10 s / 22.46 tokens per second 3.23.146.652 I slot print_timing: id 3 | task 154 | prompt processing, n_tokens = 123, progress = 0.97, t = 6.10 s / 20.16 tokens per second 3.23.724.168 I slot print_timing: id 0 | task 156 | prompt eval time = 6774.41 ms / 128 tokens ( 52.93 ms per token, 18.89 tokens per second) 3.23.724.173 I slot print_timing: id 0 | task 156 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 3.23.724.174 I slot print_timing: id 0 | task 156 | total time = 6984.57 ms / 130 tokens 3.23.724.174 I slot print_timing: id 0 | task 156 | graphs reused = 1 3.23.724.175 I slot print_timing: id 0 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.724.203 I slot release: id 0 | task 156 | stop processing: n_tokens = 129, truncated = 0 3.23.724.356 I slot print_timing: id 1 | task 155 | prompt eval time = 6774.55 ms / 130 tokens ( 52.11 ms per token, 19.19 tokens per second) 3.23.724.361 I slot print_timing: id 1 | task 155 | eval time = 210.20 ms / 2 tokens ( 210.20 ms per token, 4.76 tokens per second) 3.23.724.362 I slot print_timing: id 1 | task 155 | total time = 6984.75 ms / 132 tokens 3.23.724.362 I slot print_timing: id 1 | task 155 | graphs reused = 1 3.23.724.362 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.724.372 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 3.23.724.546 I slot print_timing: id 2 | task 157 | prompt eval time = 6774.72 ms / 141 tokens ( 48.05 ms per token, 20.81 tokens per second) 3.23.724.547 I slot print_timing: id 2 | task 157 | eval time = 210.21 ms / 2 tokens ( 210.21 ms per token, 4.76 tokens per second) 3.23.724.547 I slot print_timing: id 2 | task 157 | total time = 6984.93 ms / 143 tokens 3.23.724.548 I slot print_timing: id 2 | task 157 | graphs reused = 1 3.23.724.548 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.724.569 I slot release: id 2 | task 157 | stop processing: n_tokens = 142, truncated = 0 3.23.724.758 I slot print_timing: id 3 | task 154 | prompt eval time = 6774.88 ms / 127 tokens ( 53.35 ms per token, 18.75 tokens per second) 3.23.724.760 I slot print_timing: id 3 | task 154 | eval time = 210.26 ms / 2 tokens ( 210.26 ms per token, 4.76 tokens per second) 3.23.724.761 I slot print_timing: id 3 | task 154 | total time = 6985.14 ms / 129 tokens 3.23.724.761 I slot print_timing: id 3 | task 154 | graphs reused = 1 3.23.724.762 I slot print_timing: id 3 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.724.770 I slot release: id 3 | task 154 | stop processing: n_tokens = 128, truncated = 0 3.23.730.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 3.23.730.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 3.23.739.063 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 3.23.739.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 3.23.747.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.321 MiB) 3.23.755.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 3.23.763.604 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 3.23.763.660 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 3.23.763.694 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 3.23.763.727 I slot launch_slot_: id 3 | task 161 | processing task, is_child = 0 3.23.763.745 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 3.23.763.781 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 3.29.483.124 I slot print_timing: id 0 | task 163 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.72 s / 21.86 tokens per second 3.30.241.982 I slot print_timing: id 1 | task 162 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.72 s / 20.81 tokens per second 3.30.246.724 I slot print_timing: id 2 | task 164 | prompt processing, n_tokens = 157, progress = 0.98, t = 5.72 s / 27.45 tokens per second 3.30.251.656 I slot print_timing: id 3 | task 161 | prompt processing, n_tokens = 101, progress = 0.96, t = 5.72 s / 17.66 tokens per second 3.30.829.214 I slot print_timing: id 0 | task 163 | prompt eval time = 6855.24 ms / 129 tokens ( 53.14 ms per token, 18.82 tokens per second) 3.30.829.220 I slot print_timing: id 0 | task 163 | eval time = 210.18 ms / 2 tokens ( 210.18 ms per token, 4.76 tokens per second) 3.30.829.221 I slot print_timing: id 0 | task 163 | total time = 7065.42 ms / 131 tokens 3.30.829.221 I slot print_timing: id 0 | task 163 | graphs reused = 1 3.30.829.221 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.829.245 I slot release: id 0 | task 163 | stop processing: n_tokens = 130, truncated = 0 3.30.829.393 I slot print_timing: id 1 | task 162 | prompt eval time = 6855.39 ms / 123 tokens ( 55.73 ms per token, 17.94 tokens per second) 3.30.829.397 I slot print_timing: id 1 | task 162 | eval time = 210.20 ms / 2 tokens ( 210.20 ms per token, 4.76 tokens per second) 3.30.829.398 I slot print_timing: id 1 | task 162 | total time = 7065.59 ms / 125 tokens 3.30.829.398 I slot print_timing: id 1 | task 162 | graphs reused = 1 3.30.829.398 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.829.409 I slot release: id 1 | task 162 | stop processing: n_tokens = 124, truncated = 0 3.30.829.581 I slot print_timing: id 2 | task 164 | prompt eval time = 6855.54 ms / 161 tokens ( 42.58 ms per token, 23.48 tokens per second) 3.30.829.591 I slot print_timing: id 2 | task 164 | eval time = 210.22 ms / 2 tokens ( 210.22 ms per token, 4.76 tokens per second) 3.30.829.591 I slot print_timing: id 2 | task 164 | total time = 7065.77 ms / 163 tokens 3.30.829.591 I slot print_timing: id 2 | task 164 | graphs reused = 1 3.30.829.592 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.829.610 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 3.30.829.772 I slot print_timing: id 3 | task 161 | prompt eval time = 6855.70 ms / 105 tokens ( 65.29 ms per token, 15.32 tokens per second) 3.30.829.773 I slot print_timing: id 3 | task 161 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 3.30.829.774 I slot print_timing: id 3 | task 161 | total time = 7065.94 ms / 107 tokens 3.30.829.774 I slot print_timing: id 3 | task 161 | graphs reused = 1 3.30.829.774 I slot print_timing: id 3 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.829.781 I slot release: id 3 | task 161 | stop processing: n_tokens = 106, truncated = 0 3.30.835.937 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 3.30.835.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 3.30.844.518 I slot launch_slot_: id 3 | task 168 | processing task, is_child = 0 3.30.844.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 3.30.852.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.445 MiB) 3.30.860.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 3.30.868.514 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.215 3.30.868.570 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 3.30.868.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 3.30.868.637 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 3.30.868.657 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.173 3.30.868.689 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 3.37.371.345 I slot print_timing: id 0 | task 169 | prompt processing, n_tokens = 150, progress = 0.97, t = 6.50 s / 23.07 tokens per second 3.37.800.719 I slot print_timing: id 1 | task 170 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.50 s / 21.07 tokens per second 3.37.805.627 I slot print_timing: id 2 | task 171 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.50 s / 24.61 tokens per second 3.37.810.599 I slot print_timing: id 3 | task 168 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.50 s / 16.30 tokens per second 3.38.388.483 I slot print_timing: id 0 | task 169 | prompt eval time = 7309.56 ms / 154 tokens ( 47.46 ms per token, 21.07 tokens per second) 3.38.388.485 I slot print_timing: id 0 | task 169 | eval time = 210.22 ms / 2 tokens ( 210.22 ms per token, 4.76 tokens per second) 3.38.388.485 I slot print_timing: id 0 | task 169 | total time = 7519.78 ms / 156 tokens 3.38.388.486 I slot print_timing: id 0 | task 169 | graphs reused = 1 3.38.388.486 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.388.526 I slot release: id 0 | task 169 | stop processing: n_tokens = 155, truncated = 0 3.38.388.677 I slot print_timing: id 1 | task 170 | prompt eval time = 7309.71 ms / 141 tokens ( 51.84 ms per token, 19.29 tokens per second) 3.38.388.680 I slot print_timing: id 1 | task 170 | eval time = 210.26 ms / 2 tokens ( 210.26 ms per token, 4.76 tokens per second) 3.38.388.680 I slot print_timing: id 1 | task 170 | total time = 7519.97 ms / 143 tokens 3.38.388.680 I slot print_timing: id 1 | task 170 | graphs reused = 1 3.38.388.681 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.388.698 I slot release: id 1 | task 170 | stop processing: n_tokens = 142, truncated = 0 3.38.388.866 I slot print_timing: id 2 | task 171 | prompt eval time = 7309.89 ms / 164 tokens ( 44.57 ms per token, 22.44 tokens per second) 3.38.388.869 I slot print_timing: id 2 | task 171 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 3.38.388.870 I slot print_timing: id 2 | task 171 | total time = 7520.15 ms / 166 tokens 3.38.388.871 I slot print_timing: id 2 | task 171 | graphs reused = 1 3.38.388.871 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.388.883 I slot release: id 2 | task 171 | stop processing: n_tokens = 165, truncated = 0 3.38.389.066 I slot print_timing: id 3 | task 168 | prompt eval time = 7310.05 ms / 110 tokens ( 66.45 ms per token, 15.05 tokens per second) 3.38.389.071 I slot print_timing: id 3 | task 168 | eval time = 210.29 ms / 2 tokens ( 210.29 ms per token, 4.76 tokens per second) 3.38.389.071 I slot print_timing: id 3 | task 168 | total time = 7520.33 ms / 112 tokens 3.38.389.071 I slot print_timing: id 3 | task 168 | graphs reused = 1 3.38.389.072 I slot print_timing: id 3 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.389.081 I slot release: id 3 | task 168 | stop processing: n_tokens = 111, truncated = 0 3.38.393.912 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 3.38.393.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.38.402.486 I slot launch_slot_: id 3 | task 175 | processing task, is_child = 0 3.38.402.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.320 MiB) 3.38.410.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 3.38.419.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.38.426.923 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 3.38.426.980 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 3.38.427.024 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.197 3.38.427.057 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 3.38.427.077 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.170 3.38.427.110 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 3.44.254.865 I slot print_timing: id 0 | task 176 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.83 s / 18.19 tokens per second 3.44.552.128 I slot print_timing: id 1 | task 177 | prompt processing, n_tokens = 133, progress = 0.97, t = 5.83 s / 22.82 tokens per second 3.44.557.050 I slot print_timing: id 2 | task 178 | prompt processing, n_tokens = 144, progress = 0.97, t = 5.83 s / 24.71 tokens per second 3.44.562.003 I slot print_timing: id 3 | task 175 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.83 s / 18.19 tokens per second 3.45.139.588 I slot print_timing: id 0 | task 176 | prompt eval time = 6502.39 ms / 110 tokens ( 59.11 ms per token, 16.92 tokens per second) 3.45.139.590 I slot print_timing: id 0 | task 176 | eval time = 210.07 ms / 2 tokens ( 210.07 ms per token, 4.76 tokens per second) 3.45.139.590 I slot print_timing: id 0 | task 176 | total time = 6712.47 ms / 112 tokens 3.45.139.591 I slot print_timing: id 0 | task 176 | graphs reused = 1 3.45.139.591 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.139.613 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 3.45.139.761 I slot print_timing: id 1 | task 177 | prompt eval time = 6502.53 ms / 137 tokens ( 47.46 ms per token, 21.07 tokens per second) 3.45.139.764 I slot print_timing: id 1 | task 177 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 3.45.139.764 I slot print_timing: id 1 | task 177 | total time = 6712.63 ms / 139 tokens 3.45.139.764 I slot print_timing: id 1 | task 177 | graphs reused = 1 3.45.139.765 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.139.776 I slot release: id 1 | task 177 | stop processing: n_tokens = 138, truncated = 0 3.45.139.954 I slot print_timing: id 2 | task 178 | prompt eval time = 6502.69 ms / 148 tokens ( 43.94 ms per token, 22.76 tokens per second) 3.45.139.958 I slot print_timing: id 2 | task 178 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 3.45.139.958 I slot print_timing: id 2 | task 178 | total time = 6712.81 ms / 150 tokens 3.45.139.959 I slot print_timing: id 2 | task 178 | graphs reused = 1 3.45.139.959 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.139.969 I slot release: id 2 | task 178 | stop processing: n_tokens = 149, truncated = 0 3.45.140.134 I slot print_timing: id 3 | task 175 | prompt eval time = 6502.85 ms / 110 tokens ( 59.12 ms per token, 16.92 tokens per second) 3.45.140.136 I slot print_timing: id 3 | task 175 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 3.45.140.137 I slot print_timing: id 3 | task 175 | total time = 6712.97 ms / 112 tokens 3.45.140.137 I slot print_timing: id 3 | task 175 | graphs reused = 1 3.45.140.137 I slot print_timing: id 3 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.140.144 I slot release: id 3 | task 175 | stop processing: n_tokens = 111, truncated = 0 3.45.146.010 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 3.45.146.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.45.154.023 I slot launch_slot_: id 0 | task 183 | processing task, is_child = 0 3.45.154.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.45.161.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 3.45.169.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 3.45.177.415 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.203 3.45.177.487 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 3.45.177.529 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.188 3.45.177.564 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 3.45.177.582 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 3.45.177.618 I slot launch_slot_: id 3 | task 182 | processing task, is_child = 0 3.51.310.496 I slot print_timing: id 0 | task 183 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.13 s / 24.13 tokens per second 3.51.738.837 I slot print_timing: id 1 | task 185 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.13 s / 20.55 tokens per second 3.51.743.255 I slot print_timing: id 2 | task 184 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.13 s / 19.40 tokens per second 3.51.747.639 I slot print_timing: id 3 | task 182 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.13 s / 17.61 tokens per second 3.52.325.138 I slot print_timing: id 0 | task 183 | prompt eval time = 6937.48 ms / 152 tokens ( 45.64 ms per token, 21.91 tokens per second) 3.52.325.141 I slot print_timing: id 0 | task 183 | eval time = 210.03 ms / 2 tokens ( 210.03 ms per token, 4.76 tokens per second) 3.52.325.141 I slot print_timing: id 0 | task 183 | total time = 7147.51 ms / 154 tokens 3.52.325.142 I slot print_timing: id 0 | task 183 | graphs reused = 1 3.52.325.142 I slot print_timing: id 0 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.325.160 I slot release: id 0 | task 183 | stop processing: n_tokens = 153, truncated = 0 3.52.325.310 I slot print_timing: id 1 | task 185 | prompt eval time = 6937.62 ms / 130 tokens ( 53.37 ms per token, 18.74 tokens per second) 3.52.325.315 I slot print_timing: id 1 | task 185 | eval time = 210.04 ms / 2 tokens ( 210.04 ms per token, 4.76 tokens per second) 3.52.325.316 I slot print_timing: id 1 | task 185 | total time = 7147.66 ms / 132 tokens 3.52.325.316 I slot print_timing: id 1 | task 185 | graphs reused = 1 3.52.325.316 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.325.326 I slot release: id 1 | task 185 | stop processing: n_tokens = 131, truncated = 0 3.52.325.499 I slot print_timing: id 2 | task 184 | prompt eval time = 6937.77 ms / 123 tokens ( 56.40 ms per token, 17.73 tokens per second) 3.52.325.501 I slot print_timing: id 2 | task 184 | eval time = 210.07 ms / 2 tokens ( 210.07 ms per token, 4.76 tokens per second) 3.52.325.501 I slot print_timing: id 2 | task 184 | total time = 7147.84 ms / 125 tokens 3.52.325.501 I slot print_timing: id 2 | task 184 | graphs reused = 1 3.52.325.502 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.325.517 I slot release: id 2 | task 184 | stop processing: n_tokens = 124, truncated = 0 3.52.325.674 I slot print_timing: id 3 | task 182 | prompt eval time = 6937.92 ms / 112 tokens ( 61.95 ms per token, 16.14 tokens per second) 3.52.325.677 I slot print_timing: id 3 | task 182 | eval time = 210.08 ms / 2 tokens ( 210.08 ms per token, 4.76 tokens per second) 3.52.325.677 I slot print_timing: id 3 | task 182 | total time = 7148.00 ms / 114 tokens 3.52.325.677 I slot print_timing: id 3 | task 182 | graphs reused = 1 3.52.325.678 I slot print_timing: id 3 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.325.685 I slot release: id 3 | task 182 | stop processing: n_tokens = 113, truncated = 0 3.52.331.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 3.52.331.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.52.340.266 I slot launch_slot_: id 1 | task 189 | processing task, is_child = 0 3.52.340.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.256 MiB) 3.52.348.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 3.52.356.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.52.364.641 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 3.52.364.701 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 3.52.364.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 3.52.364.767 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 3.52.364.785 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.226 3.52.364.822 I slot launch_slot_: id 2 | task 192 | processing task, is_child = 0 3.58.639.321 I slot print_timing: id 0 | task 191 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.27 s / 24.38 tokens per second 3.59.399.101 I slot print_timing: id 1 | task 189 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.27 s / 19.76 tokens per second 3.59.403.839 I slot print_timing: id 2 | task 192 | prompt processing, n_tokens = 162, progress = 0.98, t = 6.27 s / 25.82 tokens per second 3.59.408.929 I slot print_timing: id 3 | task 190 | prompt processing, n_tokens = 110, progress = 0.96, t = 6.27 s / 17.53 tokens per second 3.59.987.289 I slot print_timing: id 0 | task 191 | prompt eval time = 7412.38 ms / 157 tokens ( 47.21 ms per token, 21.18 tokens per second) 3.59.987.291 I slot print_timing: id 0 | task 191 | eval time = 210.08 ms / 2 tokens ( 210.08 ms per token, 4.76 tokens per second) 3.59.987.292 I slot print_timing: id 0 | task 191 | total time = 7622.45 ms / 159 tokens 3.59.987.293 I slot print_timing: id 0 | task 191 | graphs reused = 1 3.59.987.293 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.987.316 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 3.59.987.464 I slot print_timing: id 1 | task 189 | prompt eval time = 7412.52 ms / 128 tokens ( 57.91 ms per token, 17.27 tokens per second) 3.59.987.469 I slot print_timing: id 1 | task 189 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 3.59.987.469 I slot print_timing: id 1 | task 189 | total time = 7622.62 ms / 130 tokens 3.59.987.469 I slot print_timing: id 1 | task 189 | graphs reused = 1 3.59.987.470 I slot print_timing: id 1 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.987.490 I slot release: id 1 | task 189 | stop processing: n_tokens = 129, truncated = 0 3.59.987.679 I slot print_timing: id 2 | task 192 | prompt eval time = 7412.68 ms / 166 tokens ( 44.65 ms per token, 22.39 tokens per second) 3.59.987.681 I slot print_timing: id 2 | task 192 | eval time = 210.14 ms / 2 tokens ( 210.14 ms per token, 4.76 tokens per second) 3.59.987.681 I slot print_timing: id 2 | task 192 | total time = 7622.82 ms / 168 tokens 3.59.987.682 I slot print_timing: id 2 | task 192 | graphs reused = 1 3.59.987.682 I slot print_timing: id 2 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.987.694 I slot release: id 2 | task 192 | stop processing: n_tokens = 167, truncated = 0 3.59.987.875 I slot print_timing: id 3 | task 190 | prompt eval time = 7412.83 ms / 114 tokens ( 65.02 ms per token, 15.38 tokens per second) 3.59.987.877 I slot print_timing: id 3 | task 190 | eval time = 210.17 ms / 2 tokens ( 210.17 ms per token, 4.76 tokens per second) 3.59.987.877 I slot print_timing: id 3 | task 190 | total time = 7623.00 ms / 116 tokens 3.59.987.878 I slot print_timing: id 3 | task 190 | graphs reused = 1 3.59.987.878 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.987.886 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 3.59.994.029 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.177 3.59.994.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.257 MiB) 4.00.006.299 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 4.00.014.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.569 MiB) 4.00.022.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 4.00.030.224 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.217 4.00.030.279 I slot launch_slot_: id 1 | task 196 | processing task, is_child = 0 4.00.030.315 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.168 4.00.030.349 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 4.00.030.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.243 4.00.030.401 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 4.06.634.809 I slot print_timing: id 0 | task 197 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.60 s / 20.74 tokens per second 4.07.065.072 I slot print_timing: id 1 | task 196 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.60 s / 15.75 tokens per second 4.07.070.211 I slot print_timing: id 2 | task 198 | prompt processing, n_tokens = 149, progress = 0.97, t = 6.60 s / 22.56 tokens per second 4.07.075.114 I slot print_timing: id 3 | task 199 | prompt processing, n_tokens = 175, progress = 0.98, t = 6.60 s / 26.50 tokens per second 4.07.653.383 I slot print_timing: id 0 | task 197 | prompt eval time = 7412.78 ms / 141 tokens ( 52.57 ms per token, 19.02 tokens per second) 4.07.653.387 I slot print_timing: id 0 | task 197 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 4.07.653.388 I slot print_timing: id 0 | task 197 | total time = 7622.97 ms / 143 tokens 4.07.653.388 I slot print_timing: id 0 | task 197 | graphs reused = 1 4.07.653.388 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.653.407 I slot release: id 0 | task 197 | stop processing: n_tokens = 142, truncated = 0 4.07.653.552 I slot print_timing: id 1 | task 196 | prompt eval time = 7412.94 ms / 108 tokens ( 68.64 ms per token, 14.57 tokens per second) 4.07.653.557 I slot print_timing: id 1 | task 196 | eval time = 210.20 ms / 2 tokens ( 210.20 ms per token, 4.76 tokens per second) 4.07.653.558 I slot print_timing: id 1 | task 196 | total time = 7623.13 ms / 110 tokens 4.07.653.558 I slot print_timing: id 1 | task 196 | graphs reused = 1 4.07.653.558 I slot print_timing: id 1 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.653.568 I slot release: id 1 | task 196 | stop processing: n_tokens = 109, truncated = 0 4.07.653.763 I slot print_timing: id 2 | task 198 | prompt eval time = 7413.09 ms / 153 tokens ( 48.45 ms per token, 20.64 tokens per second) 4.07.653.765 I slot print_timing: id 2 | task 198 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.07.653.765 I slot print_timing: id 2 | task 198 | total time = 7623.33 ms / 155 tokens 4.07.653.766 I slot print_timing: id 2 | task 198 | graphs reused = 1 4.07.653.766 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.653.776 I slot release: id 2 | task 198 | stop processing: n_tokens = 154, truncated = 0 4.07.653.969 I slot print_timing: id 3 | task 199 | prompt eval time = 7413.25 ms / 179 tokens ( 41.41 ms per token, 24.15 tokens per second) 4.07.653.971 I slot print_timing: id 3 | task 199 | eval time = 210.27 ms / 2 tokens ( 210.27 ms per token, 4.76 tokens per second) 4.07.653.971 I slot print_timing: id 3 | task 199 | total time = 7623.52 ms / 181 tokens 4.07.653.972 I slot print_timing: id 3 | task 199 | graphs reused = 1 4.07.653.972 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.653.985 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 4.07.659.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.197 4.07.659.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.07.668.261 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 4.07.668.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.07.676.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 4.07.684.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.07.693.020 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.257 4.07.696.379 I slot launch_slot_: id 1 | task 203 | processing task, is_child = 0 4.07.696.419 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 4.07.696.450 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 4.07.696.468 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 4.07.696.499 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 4.13.911.905 I slot print_timing: id 0 | task 204 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.22 s / 20.92 tokens per second 4.14.342.426 I slot print_timing: id 1 | task 203 | prompt processing, n_tokens = 112, progress = 0.97, t = 6.22 s / 18.02 tokens per second 4.14.347.389 I slot print_timing: id 2 | task 205 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.22 s / 21.08 tokens per second 4.14.352.220 I slot print_timing: id 3 | task 206 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.22 s / 24.78 tokens per second 4.14.930.478 I slot print_timing: id 0 | task 204 | prompt eval time = 7023.64 ms / 134 tokens ( 52.42 ms per token, 19.08 tokens per second) 4.14.930.481 I slot print_timing: id 0 | task 204 | eval time = 210.32 ms / 2 tokens ( 210.32 ms per token, 4.75 tokens per second) 4.14.930.482 I slot print_timing: id 0 | task 204 | total time = 7233.97 ms / 136 tokens 4.14.930.482 I slot print_timing: id 0 | task 204 | graphs reused = 1 4.14.930.483 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.930.505 I slot release: id 0 | task 204 | stop processing: n_tokens = 135, truncated = 0 4.14.930.655 I slot print_timing: id 1 | task 203 | prompt eval time = 7023.79 ms / 116 tokens ( 60.55 ms per token, 16.52 tokens per second) 4.14.930.658 I slot print_timing: id 1 | task 203 | eval time = 210.35 ms / 2 tokens ( 210.35 ms per token, 4.75 tokens per second) 4.14.930.659 I slot print_timing: id 1 | task 203 | total time = 7234.14 ms / 118 tokens 4.14.930.659 I slot print_timing: id 1 | task 203 | graphs reused = 1 4.14.930.659 I slot print_timing: id 1 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.930.669 I slot release: id 1 | task 203 | stop processing: n_tokens = 117, truncated = 0 4.14.930.837 I slot print_timing: id 2 | task 205 | prompt eval time = 7023.95 ms / 135 tokens ( 52.03 ms per token, 19.22 tokens per second) 4.14.930.841 I slot print_timing: id 2 | task 205 | eval time = 210.36 ms / 2 tokens ( 210.36 ms per token, 4.75 tokens per second) 4.14.930.841 I slot print_timing: id 2 | task 205 | total time = 7234.31 ms / 137 tokens 4.14.930.841 I slot print_timing: id 2 | task 205 | graphs reused = 1 4.14.930.842 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.930.852 I slot release: id 2 | task 205 | stop processing: n_tokens = 136, truncated = 0 4.14.931.018 I slot print_timing: id 3 | task 206 | prompt eval time = 7024.11 ms / 158 tokens ( 44.46 ms per token, 22.49 tokens per second) 4.14.931.020 I slot print_timing: id 3 | task 206 | eval time = 210.36 ms / 2 tokens ( 210.36 ms per token, 4.75 tokens per second) 4.14.931.020 I slot print_timing: id 3 | task 206 | total time = 7234.48 ms / 160 tokens 4.14.931.021 I slot print_timing: id 3 | task 206 | graphs reused = 1 4.14.931.021 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.931.031 I slot release: id 3 | task 206 | stop processing: n_tokens = 159, truncated = 0 4.14.936.874 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 4.14.949.016 I slot launch_slot_: id 1 | task 210 | processing task, is_child = 0 4.14.956.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.14.964.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 4.14.972.808 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.207 4.14.972.882 I slot launch_slot_: id 0 | task 212 | processing task, is_child = 0 4.14.972.923 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.206 4.14.976.232 I slot launch_slot_: id 2 | task 211 | processing task, is_child = 0 4.14.976.258 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.176 4.14.976.294 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 4.21.095.050 I slot print_timing: id 0 | task 212 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.12 s / 23.70 tokens per second 4.21.854.739 I slot print_timing: id 1 | task 210 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.12 s / 19.29 tokens per second 4.21.859.171 I slot print_timing: id 2 | task 211 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.12 s / 18.47 tokens per second 4.21.863.604 I slot print_timing: id 3 | task 213 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.12 s / 25.01 tokens per second 4.22.441.164 I slot print_timing: id 0 | task 212 | prompt eval time = 7254.68 ms / 149 tokens ( 48.69 ms per token, 20.54 tokens per second) 4.22.441.169 I slot print_timing: id 0 | task 212 | eval time = 210.18 ms / 2 tokens ( 210.18 ms per token, 4.76 tokens per second) 4.22.441.170 I slot print_timing: id 0 | task 212 | total time = 7464.86 ms / 151 tokens 4.22.441.170 I slot print_timing: id 0 | task 212 | graphs reused = 1 4.22.441.171 I slot print_timing: id 0 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.441.193 I slot release: id 0 | task 212 | stop processing: n_tokens = 150, truncated = 0 4.22.441.339 I slot print_timing: id 1 | task 210 | prompt eval time = 7254.82 ms / 122 tokens ( 59.47 ms per token, 16.82 tokens per second) 4.22.441.342 I slot print_timing: id 1 | task 210 | eval time = 210.20 ms / 2 tokens ( 210.20 ms per token, 4.76 tokens per second) 4.22.441.342 I slot print_timing: id 1 | task 210 | total time = 7465.02 ms / 124 tokens 4.22.441.342 I slot print_timing: id 1 | task 210 | graphs reused = 1 4.22.441.343 I slot print_timing: id 1 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.441.351 I slot release: id 1 | task 210 | stop processing: n_tokens = 123, truncated = 0 4.22.441.522 I slot print_timing: id 2 | task 211 | prompt eval time = 7254.97 ms / 117 tokens ( 62.01 ms per token, 16.13 tokens per second) 4.22.441.524 I slot print_timing: id 2 | task 211 | eval time = 210.23 ms / 2 tokens ( 210.23 ms per token, 4.76 tokens per second) 4.22.441.525 I slot print_timing: id 2 | task 211 | total time = 7465.20 ms / 119 tokens 4.22.441.525 I slot print_timing: id 2 | task 211 | graphs reused = 1 4.22.441.526 I slot print_timing: id 2 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.441.536 I slot release: id 2 | task 211 | stop processing: n_tokens = 118, truncated = 0 4.22.441.709 I slot print_timing: id 3 | task 213 | prompt eval time = 7255.11 ms / 157 tokens ( 46.21 ms per token, 21.64 tokens per second) 4.22.441.712 I slot print_timing: id 3 | task 213 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.22.441.712 I slot print_timing: id 3 | task 213 | total time = 7465.37 ms / 159 tokens 4.22.441.712 I slot print_timing: id 3 | task 213 | graphs reused = 1 4.22.441.713 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.441.724 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 4.22.447.438 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.187 4.22.464.737 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 4.22.464.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.22.472.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 4.22.480.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 4.22.488.571 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.228 4.22.488.635 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 4.22.488.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.237 4.22.488.714 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 4.22.488.746 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.177 4.22.488.787 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 4.29.841.080 I slot print_timing: id 0 | task 217 | prompt processing, n_tokens = 145, progress = 0.97, t = 7.35 s / 19.72 tokens per second 4.29.938.221 I slot print_timing: id 1 | task 218 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.35 s / 21.22 tokens per second 4.29.942.664 I slot print_timing: id 2 | task 219 | prompt processing, n_tokens = 150, progress = 0.97, t = 7.35 s / 20.40 tokens per second 4.29.947.077 I slot print_timing: id 3 | task 220 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.35 s / 20.54 tokens per second 4.30.524.354 I slot print_timing: id 0 | task 217 | prompt eval time = 7825.57 ms / 149 tokens ( 52.52 ms per token, 19.04 tokens per second) 4.30.524.357 I slot print_timing: id 0 | task 217 | eval time = 209.99 ms / 2 tokens ( 209.99 ms per token, 4.76 tokens per second) 4.30.524.359 I slot print_timing: id 0 | task 217 | total time = 8035.55 ms / 151 tokens 4.30.524.359 I slot print_timing: id 0 | task 217 | graphs reused = 1 4.30.524.359 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.524.382 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 4.30.524.532 I slot print_timing: id 1 | task 218 | prompt eval time = 7825.70 ms / 160 tokens ( 48.91 ms per token, 20.45 tokens per second) 4.30.524.537 I slot print_timing: id 1 | task 218 | eval time = 210.02 ms / 2 tokens ( 210.02 ms per token, 4.76 tokens per second) 4.30.524.538 I slot print_timing: id 1 | task 218 | total time = 8035.72 ms / 162 tokens 4.30.524.538 I slot print_timing: id 1 | task 218 | graphs reused = 1 4.30.524.538 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.524.554 I slot release: id 1 | task 218 | stop processing: n_tokens = 161, truncated = 0 4.30.524.718 I slot print_timing: id 2 | task 219 | prompt eval time = 7825.85 ms / 154 tokens ( 50.82 ms per token, 19.68 tokens per second) 4.30.524.723 I slot print_timing: id 2 | task 219 | eval time = 210.04 ms / 2 tokens ( 210.04 ms per token, 4.76 tokens per second) 4.30.524.724 I slot print_timing: id 2 | task 219 | total time = 8035.89 ms / 156 tokens 4.30.524.724 I slot print_timing: id 2 | task 219 | graphs reused = 1 4.30.524.724 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.524.735 I slot release: id 2 | task 219 | stop processing: n_tokens = 155, truncated = 0 4.30.524.898 I slot print_timing: id 3 | task 220 | prompt eval time = 7826.00 ms / 155 tokens ( 50.49 ms per token, 19.81 tokens per second) 4.30.524.901 I slot print_timing: id 3 | task 220 | eval time = 210.06 ms / 2 tokens ( 210.06 ms per token, 4.76 tokens per second) 4.30.524.901 I slot print_timing: id 3 | task 220 | total time = 8036.06 ms / 157 tokens 4.30.524.901 I slot print_timing: id 3 | task 220 | graphs reused = 1 4.30.524.901 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.524.913 I slot release: id 3 | task 220 | stop processing: n_tokens = 156, truncated = 0 4.30.530.795 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.187 4.30.530.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.30.542.804 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 4.30.550.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 4.30.558.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.30.566.494 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.174 4.30.566.571 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 4.30.566.617 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 4.30.566.653 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 4.30.566.675 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.179 4.30.566.719 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 4.35.925.641 I slot print_timing: id 0 | task 224 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.36 s / 18.29 tokens per second 4.37.051.812 I slot print_timing: id 1 | task 225 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.36 s / 20.53 tokens per second 4.37.056.250 I slot print_timing: id 2 | task 226 | prompt processing, n_tokens = 181, progress = 0.98, t = 5.36 s / 33.78 tokens per second 4.37.060.691 I slot print_timing: id 3 | task 227 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.36 s / 19.22 tokens per second 4.37.638.268 I slot print_timing: id 0 | task 224 | prompt eval time = 6861.30 ms / 102 tokens ( 67.27 ms per token, 14.87 tokens per second) 4.37.638.270 I slot print_timing: id 0 | task 224 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 4.37.638.270 I slot print_timing: id 0 | task 224 | total time = 7071.53 ms / 104 tokens 4.37.638.271 I slot print_timing: id 0 | task 224 | graphs reused = 1 4.37.638.271 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.638.292 I slot release: id 0 | task 224 | stop processing: n_tokens = 103, truncated = 0 4.37.638.434 I slot print_timing: id 1 | task 225 | prompt eval time = 6861.44 ms / 114 tokens ( 60.19 ms per token, 16.61 tokens per second) 4.37.638.436 I slot print_timing: id 1 | task 225 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.37.638.436 I slot print_timing: id 1 | task 225 | total time = 7071.69 ms / 116 tokens 4.37.638.437 I slot print_timing: id 1 | task 225 | graphs reused = 1 4.37.638.437 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.638.450 I slot release: id 1 | task 225 | stop processing: n_tokens = 115, truncated = 0 4.37.638.608 I slot print_timing: id 2 | task 226 | prompt eval time = 6861.59 ms / 185 tokens ( 37.09 ms per token, 26.96 tokens per second) 4.37.638.609 I slot print_timing: id 2 | task 226 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.37.638.610 I slot print_timing: id 2 | task 226 | total time = 7071.85 ms / 187 tokens 4.37.638.610 I slot print_timing: id 2 | task 226 | graphs reused = 1 4.37.638.610 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.638.620 I slot release: id 2 | task 226 | stop processing: n_tokens = 186, truncated = 0 4.37.638.791 I slot print_timing: id 3 | task 227 | prompt eval time = 6861.77 ms / 107 tokens ( 64.13 ms per token, 15.59 tokens per second) 4.37.638.793 I slot print_timing: id 3 | task 227 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.37.638.793 I slot print_timing: id 3 | task 227 | total time = 7072.02 ms / 109 tokens 4.37.638.794 I slot print_timing: id 3 | task 227 | graphs reused = 1 4.37.638.794 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.638.801 I slot release: id 3 | task 227 | stop processing: n_tokens = 108, truncated = 0 4.37.644.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.272 4.37.644.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 4.37.653.730 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 4.37.653.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.569 MiB) 4.37.661.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.37.678.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.37.686.119 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 4.37.686.184 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 4.37.686.218 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.151 4.37.689.565 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 4.37.689.588 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.259 4.37.689.624 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 4.43.353.635 I slot print_timing: id 0 | task 231 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.66 s / 20.83 tokens per second 4.44.126.161 I slot print_timing: id 1 | task 232 | prompt processing, n_tokens = 122, progress = 0.97, t = 5.66 s / 21.54 tokens per second 4.44.130.871 I slot print_timing: id 2 | task 233 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.66 s / 18.71 tokens per second 4.44.135.821 I slot print_timing: id 3 | task 234 | prompt processing, n_tokens = 160, progress = 0.98, t = 5.66 s / 28.25 tokens per second 4.44.713.570 I slot print_timing: id 0 | task 231 | prompt eval time = 6814.14 ms / 122 tokens ( 55.85 ms per token, 17.90 tokens per second) 4.44.713.572 I slot print_timing: id 0 | task 231 | eval time = 209.79 ms / 2 tokens ( 209.79 ms per token, 4.77 tokens per second) 4.44.713.573 I slot print_timing: id 0 | task 231 | total time = 7023.93 ms / 124 tokens 4.44.713.573 I slot print_timing: id 0 | task 231 | graphs reused = 1 4.44.713.573 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.713.595 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 4.44.713.744 I slot print_timing: id 1 | task 232 | prompt eval time = 6814.29 ms / 126 tokens ( 54.08 ms per token, 18.49 tokens per second) 4.44.713.746 I slot print_timing: id 1 | task 232 | eval time = 209.81 ms / 2 tokens ( 209.81 ms per token, 4.77 tokens per second) 4.44.713.746 I slot print_timing: id 1 | task 232 | total time = 7024.10 ms / 128 tokens 4.44.713.746 I slot print_timing: id 1 | task 232 | graphs reused = 1 4.44.713.747 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.713.755 I slot release: id 1 | task 232 | stop processing: n_tokens = 127, truncated = 0 4.44.713.919 I slot print_timing: id 2 | task 233 | prompt eval time = 6814.45 ms / 110 tokens ( 61.95 ms per token, 16.14 tokens per second) 4.44.713.920 I slot print_timing: id 2 | task 233 | eval time = 209.82 ms / 2 tokens ( 209.82 ms per token, 4.77 tokens per second) 4.44.713.921 I slot print_timing: id 2 | task 233 | total time = 7024.27 ms / 112 tokens 4.44.713.921 I slot print_timing: id 2 | task 233 | graphs reused = 1 4.44.713.921 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.713.928 I slot release: id 2 | task 233 | stop processing: n_tokens = 111, truncated = 0 4.44.714.106 I slot print_timing: id 3 | task 234 | prompt eval time = 6814.60 ms / 164 tokens ( 41.55 ms per token, 24.07 tokens per second) 4.44.714.109 I slot print_timing: id 3 | task 234 | eval time = 209.84 ms / 2 tokens ( 209.84 ms per token, 4.77 tokens per second) 4.44.714.110 I slot print_timing: id 3 | task 234 | total time = 7024.44 ms / 166 tokens 4.44.714.110 I slot print_timing: id 3 | task 234 | graphs reused = 1 4.44.714.110 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.714.118 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 4.44.719.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 4.44.728.653 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 4.44.728.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 4.44.736.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.44.744.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 4.44.752.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.228 4.44.752.204 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 4.44.752.242 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.220 4.44.752.279 I slot launch_slot_: id 1 | task 238 | processing task, is_child = 0 4.44.752.300 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.170 4.44.755.622 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 4.50.773.249 I slot print_timing: id 0 | task 239 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.02 s / 20.11 tokens per second 4.50.870.848 I slot print_timing: id 1 | task 238 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.02 s / 19.61 tokens per second 4.50.875.267 I slot print_timing: id 2 | task 240 | prompt processing, n_tokens = 133, progress = 0.97, t = 6.02 s / 22.10 tokens per second 4.50.879.697 I slot print_timing: id 3 | task 241 | prompt processing, n_tokens = 134, progress = 0.97, t = 6.02 s / 22.27 tokens per second 4.51.456.987 I slot print_timing: id 0 | task 239 | prompt eval time = 6491.23 ms / 125 tokens ( 51.93 ms per token, 19.26 tokens per second) 4.51.456.990 I slot print_timing: id 0 | task 239 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 4.51.456.991 I slot print_timing: id 0 | task 239 | total time = 6701.36 ms / 127 tokens 4.51.456.992 I slot print_timing: id 0 | task 239 | graphs reused = 1 4.51.456.992 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.457.013 I slot release: id 0 | task 239 | stop processing: n_tokens = 126, truncated = 0 4.51.457.160 I slot print_timing: id 1 | task 238 | prompt eval time = 6491.37 ms / 122 tokens ( 53.21 ms per token, 18.79 tokens per second) 4.51.457.163 I slot print_timing: id 1 | task 238 | eval time = 210.14 ms / 2 tokens ( 210.14 ms per token, 4.76 tokens per second) 4.51.457.163 I slot print_timing: id 1 | task 238 | total time = 6701.51 ms / 124 tokens 4.51.457.163 I slot print_timing: id 1 | task 238 | graphs reused = 1 4.51.457.164 I slot print_timing: id 1 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.457.180 I slot release: id 1 | task 238 | stop processing: n_tokens = 123, truncated = 0 4.51.457.339 I slot print_timing: id 2 | task 240 | prompt eval time = 6491.53 ms / 137 tokens ( 47.38 ms per token, 21.10 tokens per second) 4.51.457.340 I slot print_timing: id 2 | task 240 | eval time = 210.15 ms / 2 tokens ( 210.15 ms per token, 4.76 tokens per second) 4.51.457.340 I slot print_timing: id 2 | task 240 | total time = 6701.68 ms / 139 tokens 4.51.457.341 I slot print_timing: id 2 | task 240 | graphs reused = 1 4.51.457.341 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.457.354 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 4.51.457.515 I slot print_timing: id 3 | task 241 | prompt eval time = 6491.69 ms / 138 tokens ( 47.04 ms per token, 21.26 tokens per second) 4.51.457.517 I slot print_timing: id 3 | task 241 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 4.51.457.517 I slot print_timing: id 3 | task 241 | total time = 6701.84 ms / 140 tokens 4.51.457.518 I slot print_timing: id 3 | task 241 | graphs reused = 1 4.51.457.518 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.457.534 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 4.51.463.330 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.222 4.51.472.182 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 4.51.472.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 4.51.480.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 4.51.489.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.51.497.383 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.228 4.51.500.901 I slot launch_slot_: id 1 | task 245 | processing task, is_child = 0 4.51.500.940 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.203 4.51.500.972 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 4.51.500.991 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 4.51.501.021 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 4.58.133.786 I slot print_timing: id 0 | task 246 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.63 s / 17.49 tokens per second 4.58.567.343 I slot print_timing: id 1 | task 245 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.63 s / 23.22 tokens per second 4.58.572.333 I slot print_timing: id 2 | task 247 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.63 s / 20.50 tokens per second 4.58.577.135 I slot print_timing: id 3 | task 248 | prompt processing, n_tokens = 164, progress = 0.98, t = 6.63 s / 24.73 tokens per second 4.59.155.013 I slot print_timing: id 0 | task 246 | prompt eval time = 7443.84 ms / 120 tokens ( 62.03 ms per token, 16.12 tokens per second) 4.59.155.015 I slot print_timing: id 0 | task 246 | eval time = 210.14 ms / 2 tokens ( 210.14 ms per token, 4.76 tokens per second) 4.59.155.016 I slot print_timing: id 0 | task 246 | total time = 7653.98 ms / 122 tokens 4.59.155.017 I slot print_timing: id 0 | task 246 | graphs reused = 1 4.59.155.017 I slot print_timing: id 0 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.155.039 I slot release: id 0 | task 246 | stop processing: n_tokens = 121, truncated = 0 4.59.155.192 I slot print_timing: id 1 | task 245 | prompt eval time = 7444.00 ms / 158 tokens ( 47.11 ms per token, 21.23 tokens per second) 4.59.155.194 I slot print_timing: id 1 | task 245 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 4.59.155.195 I slot print_timing: id 1 | task 245 | total time = 7654.15 ms / 160 tokens 4.59.155.195 I slot print_timing: id 1 | task 245 | graphs reused = 1 4.59.155.195 I slot print_timing: id 1 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.155.206 I slot release: id 1 | task 245 | stop processing: n_tokens = 159, truncated = 0 4.59.155.377 I slot print_timing: id 2 | task 247 | prompt eval time = 7444.16 ms / 140 tokens ( 53.17 ms per token, 18.81 tokens per second) 4.59.155.378 I slot print_timing: id 2 | task 247 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 4.59.155.379 I slot print_timing: id 2 | task 247 | total time = 7654.33 ms / 142 tokens 4.59.155.379 I slot print_timing: id 2 | task 247 | graphs reused = 1 4.59.155.379 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.155.396 I slot release: id 2 | task 247 | stop processing: n_tokens = 141, truncated = 0 4.59.155.569 I slot print_timing: id 3 | task 248 | prompt eval time = 7444.31 ms / 168 tokens ( 44.31 ms per token, 22.57 tokens per second) 4.59.155.571 I slot print_timing: id 3 | task 248 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 4.59.155.571 I slot print_timing: id 3 | task 248 | total time = 7654.51 ms / 170 tokens 4.59.155.571 I slot print_timing: id 3 | task 248 | graphs reused = 1 4.59.155.571 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.155.582 I slot release: id 3 | task 248 | stop processing: n_tokens = 169, truncated = 0 4.59.161.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 4.59.169.414 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 4.59.169.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 4.59.177.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.881 MiB) 4.59.185.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.507 MiB) 4.59.193.264 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 4.59.196.624 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 4.59.196.668 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.199 4.59.196.703 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 4.59.196.722 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.166 4.59.196.755 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 5.05.835.413 I slot print_timing: id 0 | task 252 | prompt processing, n_tokens = 99, progress = 0.96, t = 6.64 s / 14.91 tokens per second 5.06.267.366 I slot print_timing: id 1 | task 253 | prompt processing, n_tokens = 129, progress = 0.97, t = 6.64 s / 19.43 tokens per second 5.06.272.295 I slot print_timing: id 2 | task 254 | prompt processing, n_tokens = 178, progress = 0.98, t = 6.64 s / 26.81 tokens per second 5.06.277.102 I slot print_timing: id 3 | task 255 | prompt processing, n_tokens = 151, progress = 0.97, t = 6.64 s / 22.75 tokens per second 5.06.855.177 I slot print_timing: id 0 | task 252 | prompt eval time = 7448.34 ms / 103 tokens ( 72.31 ms per token, 13.83 tokens per second) 5.06.855.181 I slot print_timing: id 0 | task 252 | eval time = 210.07 ms / 2 tokens ( 210.07 ms per token, 4.76 tokens per second) 5.06.855.182 I slot print_timing: id 0 | task 252 | total time = 7658.41 ms / 105 tokens 5.06.855.182 I slot print_timing: id 0 | task 252 | graphs reused = 1 5.06.855.183 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.855.204 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 5.06.855.351 I slot print_timing: id 1 | task 253 | prompt eval time = 7448.48 ms / 133 tokens ( 56.00 ms per token, 17.86 tokens per second) 5.06.855.356 I slot print_timing: id 1 | task 253 | eval time = 210.10 ms / 2 tokens ( 210.10 ms per token, 4.76 tokens per second) 5.06.855.356 I slot print_timing: id 1 | task 253 | total time = 7658.58 ms / 135 tokens 5.06.855.356 I slot print_timing: id 1 | task 253 | graphs reused = 1 5.06.855.357 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.855.367 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 5.06.855.528 I slot print_timing: id 2 | task 254 | prompt eval time = 7448.63 ms / 182 tokens ( 40.93 ms per token, 24.43 tokens per second) 5.06.855.530 I slot print_timing: id 2 | task 254 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 5.06.855.531 I slot print_timing: id 2 | task 254 | total time = 7658.74 ms / 184 tokens 5.06.855.531 I slot print_timing: id 2 | task 254 | graphs reused = 1 5.06.855.531 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.855.545 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 5.06.855.705 I slot print_timing: id 3 | task 255 | prompt eval time = 7448.79 ms / 155 tokens ( 48.06 ms per token, 20.81 tokens per second) 5.06.855.707 I slot print_timing: id 3 | task 255 | eval time = 210.12 ms / 2 tokens ( 210.12 ms per token, 4.76 tokens per second) 5.06.855.707 I slot print_timing: id 3 | task 255 | total time = 7658.91 ms / 157 tokens 5.06.855.708 I slot print_timing: id 3 | task 255 | graphs reused = 1 5.06.855.708 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.855.718 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 5.06.860.834 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.269 5.06.868.847 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 5.06.868.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.568 MiB) 5.06.876.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 5.06.884.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 5.06.892.540 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.209 5.06.892.610 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 5.10.677.276 I slot print_timing: id 0 | task 259 | prompt eval time = 3519.12 ms / 124 tokens ( 28.38 ms per token, 35.24 tokens per second) 5.10.677.279 I slot print_timing: id 0 | task 259 | eval time = 265.49 ms / 2 tokens ( 265.49 ms per token, 3.77 tokens per second) 5.10.677.280 I slot print_timing: id 0 | task 259 | total time = 3784.61 ms / 126 tokens 5.10.677.280 I slot print_timing: id 0 | task 259 | graphs reused = 1 5.10.677.280 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.677.299 I slot release: id 0 | task 259 | stop processing: n_tokens = 125, truncated = 0 5.10.677.452 I slot print_timing: id 1 | task 260 | prompt eval time = 3519.27 ms / 144 tokens ( 24.44 ms per token, 40.92 tokens per second) 5.10.677.453 I slot print_timing: id 1 | task 260 | eval time = 265.51 ms / 2 tokens ( 265.51 ms per token, 3.77 tokens per second) 5.10.677.454 I slot print_timing: id 1 | task 260 | total time = 3784.78 ms / 146 tokens 5.10.677.454 I slot print_timing: id 1 | task 260 | graphs reused = 1 5.10.677.454 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.677.462 I slot release: id 1 | task 260 | stop processing: n_tokens = 145, truncated = 0 5.10.694.033 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 79102597350 5.10.694.129 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 5.10.694.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 5.10.701.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 5.10.709.868 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 79102597523 5.10.709.912 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 5.10.709.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 79106419104 5.10.709.977 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 5.10.709.993 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 79106419267 5.10.710.028 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 5.16.394.175 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.69 tokens per second 5.17.568.899 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.69 tokens per second 5.17.573.762 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.69 tokens per second 5.17.578.166 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.69 tokens per second 5.17.587.833 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.17.587.854 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.17.587.867 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.17.587.879 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.43.730.293 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 727, progress = 0.58, t = 33.02 s / 22.02 tokens per second 5.44.039.859 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 33.02 s / 21.74 tokens per second 5.44.044.269 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 699, progress = 0.58, t = 33.02 s / 21.17 tokens per second 5.44.048.712 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 714, progress = 0.58, t = 33.02 s / 21.62 tokens per second 6.02.747.606 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.04 s / 21.62 tokens per second 6.03.058.127 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.04 s / 21.62 tokens per second 6.03.062.533 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.93, t = 52.04 s / 21.62 tokens per second 6.03.074.246 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.04 s / 21.62 tokens per second 6.08.204.813 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1239, progress = 1.00, t = 57.49 s / 21.55 tokens per second 6.08.517.049 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 57.49 s / 21.39 tokens per second 6.08.530.787 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1211, progress = 1.00, t = 57.49 s / 21.06 tokens per second 6.08.545.102 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1226, progress = 1.00, t = 57.49 s / 21.32 tokens per second 6.20.472.167 I slot print_timing: id 2 | task 264 | prompt eval time = 58217.97 ms / 1215 tokens ( 47.92 ms per token, 20.87 tokens per second) 6.20.472.173 I slot print_timing: id 2 | task 264 | eval time = 11544.13 ms / 56 tokens ( 209.89 ms per token, 4.76 tokens per second) 6.20.472.173 I slot print_timing: id 2 | task 264 | total time = 69762.10 ms / 1271 tokens 6.20.472.174 I slot print_timing: id 2 | task 264 | graphs reused = 56 6.20.472.174 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.472.220 I slot release: id 2 | task 264 | stop processing: n_tokens = 1270, truncated = 0 6.20.757.666 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.902 6.20.757.701 I slot launch_slot_: id 2 | task 330 | processing task, is_child = 0 6.25.359.939 I slot print_timing: id 3 | task 265 | prompt eval time = 58218.13 ms / 1230 tokens ( 47.33 ms per token, 21.13 tokens per second) 6.25.359.943 I slot print_timing: id 3 | task 265 | eval time = 16431.73 ms / 70 tokens ( 238.14 ms per token, 4.20 tokens per second) 6.25.359.943 I slot print_timing: id 3 | task 265 | total time = 74649.86 ms / 1300 tokens 6.25.359.944 I slot print_timing: id 3 | task 265 | graphs reused = 66 6.25.359.944 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.359.987 I slot release: id 3 | task 265 | stop processing: n_tokens = 1299, truncated = 0 6.25.559.169 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.882 6.25.559.202 I slot launch_slot_: id 3 | task 345 | processing task, is_child = 0 6.33.684.107 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 4.00 t/s, tg_3s = 4.04 t/s 6.33.684.259 I slot print_timing: id 1 | task 267 | n_gen = 100, tg = 4.00 t/s, tg_3s = 4.04 t/s 6.36.831.865 I slot print_timing: id 0 | task 266 | n_gen = 115, tg = 4.09 t/s, tg_3s = 4.77 t/s 6.36.832.029 I slot print_timing: id 1 | task 267 | n_gen = 115, tg = 4.09 t/s, tg_3s = 4.77 t/s 6.39.981.299 I slot print_timing: id 0 | task 266 | n_gen = 130, tg = 4.15 t/s, tg_3s = 4.76 t/s 6.39.981.443 I slot print_timing: id 1 | task 267 | n_gen = 130, tg = 4.15 t/s, tg_3s = 4.76 t/s 6.43.130.553 I slot print_timing: id 0 | task 266 | n_gen = 145, tg = 4.21 t/s, tg_3s = 4.76 t/s 6.43.130.698 I slot print_timing: id 1 | task 267 | n_gen = 145, tg = 4.21 t/s, tg_3s = 4.76 t/s 6.45.860.833 I slot print_timing: id 2 | task 330 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 6.46.280.491 I slot print_timing: id 0 | task 266 | n_gen = 160, tg = 4.26 t/s, tg_3s = 4.76 t/s 6.46.280.628 I slot print_timing: id 1 | task 267 | n_gen = 160, tg = 4.26 t/s, tg_3s = 4.76 t/s 6.48.800.577 I slot print_timing: id 3 | task 345 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 6.49.010.630 I slot print_timing: id 2 | task 330 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.76 t/s 6.49.430.202 I slot print_timing: id 0 | task 266 | n_gen = 175, tg = 4.30 t/s, tg_3s = 4.76 t/s 6.49.430.343 I slot print_timing: id 1 | task 267 | n_gen = 175, tg = 4.30 t/s, tg_3s = 4.76 t/s 6.51.951.083 I slot print_timing: id 3 | task 345 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 6.52.160.922 I slot print_timing: id 2 | task 330 | n_gen = 130, tg = 4.43 t/s, tg_3s = 4.76 t/s 6.52.581.112 I slot print_timing: id 0 | task 266 | n_gen = 190, tg = 4.33 t/s, tg_3s = 4.76 t/s 6.52.581.250 I slot print_timing: id 1 | task 267 | n_gen = 190, tg = 4.33 t/s, tg_3s = 4.76 t/s 6.55.103.146 I slot print_timing: id 3 | task 345 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 6.55.313.008 I slot print_timing: id 2 | task 330 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.76 t/s 6.55.732.760 I slot print_timing: id 0 | task 266 | n_gen = 205, tg = 4.36 t/s, tg_3s = 4.76 t/s 6.55.732.911 I slot print_timing: id 1 | task 267 | n_gen = 205, tg = 4.36 t/s, tg_3s = 4.76 t/s 6.58.254.833 I slot print_timing: id 3 | task 345 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 6.58.464.635 I slot print_timing: id 2 | task 330 | n_gen = 160, tg = 4.49 t/s, tg_3s = 4.76 t/s 6.58.884.760 I slot print_timing: id 0 | task 266 | n_gen = 220, tg = 4.38 t/s, tg_3s = 4.76 t/s 6.58.884.908 I slot print_timing: id 1 | task 267 | n_gen = 220, tg = 4.38 t/s, tg_3s = 4.76 t/s 7.01.406.980 I slot print_timing: id 3 | task 345 | n_gen = 160, tg = 4.76 t/s, tg_3s = 4.76 t/s 7.01.617.096 I slot print_timing: id 2 | task 330 | n_gen = 175, tg = 4.51 t/s, tg_3s = 4.76 t/s 7.02.037.244 I slot print_timing: id 0 | task 266 | n_gen = 235, tg = 4.41 t/s, tg_3s = 4.76 t/s 7.02.037.399 I slot print_timing: id 1 | task 267 | n_gen = 235, tg = 4.41 t/s, tg_3s = 4.76 t/s 7.03.718.795 I slot print_timing: id 3 | task 345 | prompt eval time = 2456.63 ms / 139 tokens ( 17.67 ms per token, 56.58 tokens per second) 7.03.718.798 I slot print_timing: id 3 | task 345 | eval time = 35702.96 ms / 171 tokens ( 210.02 ms per token, 4.76 tokens per second) 7.03.718.799 I slot print_timing: id 3 | task 345 | total time = 38159.58 ms / 310 tokens 7.03.718.799 I slot print_timing: id 3 | task 345 | graphs reused = 235 7.03.718.800 I slot print_timing: id 3 | task 345 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.718.851 I slot release: id 3 | task 345 | stop processing: n_tokens = 1434, truncated = 0 7.03.918.629 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.799 7.03.918.664 I slot launch_slot_: id 3 | task 519 | processing task, is_child = 0 7.05.974.480 I slot print_timing: id 0 | task 266 | n_gen = 245, tg = 4.28 t/s, tg_3s = 2.54 t/s 7.05.974.641 I slot print_timing: id 1 | task 267 | n_gen = 245, tg = 4.28 t/s, tg_3s = 2.54 t/s 7.05.974.862 I slot print_timing: id 2 | task 330 | n_gen = 187, tg = 4.33 t/s, tg_3s = 2.75 t/s 7.09.104.668 I slot print_timing: id 0 | task 266 | n_gen = 259, tg = 4.29 t/s, tg_3s = 4.47 t/s 7.09.104.818 I slot print_timing: id 1 | task 267 | n_gen = 259, tg = 4.29 t/s, tg_3s = 4.47 t/s 7.09.104.970 I slot print_timing: id 2 | task 330 | n_gen = 201, tg = 4.34 t/s, tg_3s = 4.47 t/s 7.12.257.217 I slot print_timing: id 0 | task 266 | n_gen = 274, tg = 4.31 t/s, tg_3s = 4.76 t/s 7.12.257.364 I slot print_timing: id 1 | task 267 | n_gen = 274, tg = 4.31 t/s, tg_3s = 4.76 t/s 7.12.257.512 I slot print_timing: id 2 | task 330 | n_gen = 216, tg = 4.37 t/s, tg_3s = 4.76 t/s 7.15.409.929 I slot print_timing: id 0 | task 266 | n_gen = 289, tg = 4.33 t/s, tg_3s = 4.76 t/s 7.15.410.078 I slot print_timing: id 1 | task 267 | n_gen = 289, tg = 4.33 t/s, tg_3s = 4.76 t/s 7.15.410.240 I slot print_timing: id 2 | task 330 | n_gen = 231, tg = 4.39 t/s, tg_3s = 4.76 t/s 7.18.565.494 I slot print_timing: id 0 | task 266 | n_gen = 304, tg = 4.35 t/s, tg_3s = 4.75 t/s 7.18.565.640 I slot print_timing: id 1 | task 267 | n_gen = 304, tg = 4.35 t/s, tg_3s = 4.75 t/s 7.18.565.790 I slot print_timing: id 2 | task 330 | n_gen = 246, tg = 4.41 t/s, tg_3s = 4.75 t/s 7.20.037.353 I slot print_timing: id 2 | task 330 | prompt eval time = 2290.46 ms / 132 tokens ( 17.35 ms per token, 57.63 tokens per second) 7.20.037.358 I slot print_timing: id 2 | task 330 | eval time = 56989.19 ms / 253 tokens ( 226.15 ms per token, 4.42 tokens per second) 7.20.037.359 I slot print_timing: id 2 | task 330 | total time = 59279.65 ms / 385 tokens 7.20.037.359 I slot print_timing: id 2 | task 330 | graphs reused = 298 7.20.037.360 I slot print_timing: id 2 | task 330 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.037.410 I slot release: id 2 | task 330 | stop processing: n_tokens = 1509, truncated = 0 7.20.322.954 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.759 7.20.322.989 I slot launch_slot_: id 2 | task 588 | processing task, is_child = 0 7.22.111.326 I slot print_timing: id 0 | task 266 | n_gen = 313, tg = 4.26 t/s, tg_3s = 2.54 t/s 7.22.111.498 I slot print_timing: id 1 | task 267 | n_gen = 313, tg = 4.26 t/s, tg_3s = 2.54 t/s 7.23.438.827 I slot print_timing: id 1 | task 267 | prompt eval time = 58217.80 ms / 1234 tokens ( 47.18 ms per token, 21.20 tokens per second) 7.23.438.833 I slot print_timing: id 1 | task 267 | eval time = 74510.97 ms / 318 tokens ( 235.05 ms per token, 4.25 tokens per second) 7.23.438.834 I slot print_timing: id 1 | task 267 | total time = 132728.77 ms / 1552 tokens 7.23.438.834 I slot print_timing: id 1 | task 267 | graphs reused = 301 7.23.438.835 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.438.881 I slot release: id 1 | task 267 | stop processing: n_tokens = 1551, truncated = 0 7.23.723.905 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.739 7.23.723.943 I slot launch_slot_: id 1 | task 596 | processing task, is_child = 0 7.25.933.946 I slot print_timing: id 0 | task 266 | n_gen = 320, tg = 4.14 t/s, tg_3s = 1.83 t/s 7.29.003.223 I slot print_timing: id 0 | task 266 | n_gen = 333, tg = 4.15 t/s, tg_3s = 4.24 t/s 7.31.524.246 I slot print_timing: id 3 | task 519 | n_gen = 100, tg = 3.94 t/s, tg_3s = 3.98 t/s 7.32.154.088 I slot print_timing: id 0 | task 266 | n_gen = 348, tg = 4.17 t/s, tg_3s = 4.76 t/s 7.34.674.506 I slot print_timing: id 3 | task 519 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.76 t/s 7.35.304.099 I slot print_timing: id 0 | task 266 | n_gen = 363, tg = 4.19 t/s, tg_3s = 4.76 t/s 7.37.825.764 I slot print_timing: id 3 | task 519 | n_gen = 130, tg = 4.10 t/s, tg_3s = 4.76 t/s 7.38.455.790 I slot print_timing: id 0 | task 266 | n_gen = 378, tg = 4.21 t/s, tg_3s = 4.76 t/s 7.40.977.865 I slot print_timing: id 3 | task 519 | n_gen = 145, tg = 4.16 t/s, tg_3s = 4.76 t/s 7.41.608.096 I slot print_timing: id 0 | task 266 | n_gen = 393, tg = 4.23 t/s, tg_3s = 4.76 t/s 7.44.130.509 I slot print_timing: id 3 | task 519 | n_gen = 160, tg = 4.21 t/s, tg_3s = 4.76 t/s 7.44.760.500 I slot print_timing: id 0 | task 266 | n_gen = 408, tg = 4.25 t/s, tg_3s = 4.76 t/s 7.45.811.196 I slot print_timing: id 2 | task 588 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.31 t/s 7.47.282.412 I slot print_timing: id 1 | task 596 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 7.47.282.690 I slot print_timing: id 3 | task 519 | n_gen = 175, tg = 4.25 t/s, tg_3s = 4.76 t/s 7.47.912.336 I slot print_timing: id 0 | task 266 | n_gen = 423, tg = 4.26 t/s, tg_3s = 4.76 t/s 7.48.332.540 I slot print_timing: id 2 | task 588 | prompt eval time = 2273.14 ms / 114 tokens ( 19.94 ms per token, 50.15 tokens per second) 7.48.332.546 I slot print_timing: id 2 | task 588 | eval time = 25736.41 ms / 112 tokens ( 231.86 ms per token, 4.31 tokens per second) 7.48.332.546 I slot print_timing: id 2 | task 588 | total time = 28009.55 ms / 226 tokens 7.48.332.547 I slot print_timing: id 2 | task 588 | graphs reused = 404 7.48.332.547 I slot print_timing: id 2 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.332.597 I slot release: id 2 | task 588 | stop processing: n_tokens = 1350, truncated = 0 7.48.618.466 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.849 7.48.618.501 I slot launch_slot_: id 2 | task 704 | processing task, is_child = 0 7.51.114.184 I slot print_timing: id 0 | task 266 | n_gen = 427, tg = 4.17 t/s, tg_3s = 1.25 t/s 7.51.114.343 I slot print_timing: id 1 | task 596 | n_gen = 107, tg = 4.30 t/s, tg_3s = 1.83 t/s 7.51.114.512 I slot print_timing: id 3 | task 519 | n_gen = 182, tg = 4.05 t/s, tg_3s = 1.83 t/s 7.54.122.215 I slot print_timing: id 0 | task 266 | n_gen = 440, tg = 4.17 t/s, tg_3s = 4.32 t/s 7.54.122.369 I slot print_timing: id 1 | task 596 | n_gen = 120, tg = 4.31 t/s, tg_3s = 4.32 t/s 7.54.122.650 I slot print_timing: id 3 | task 519 | n_gen = 195, tg = 4.06 t/s, tg_3s = 4.32 t/s 7.57.274.328 I slot print_timing: id 0 | task 266 | n_gen = 455, tg = 4.19 t/s, tg_3s = 4.76 t/s 7.57.274.486 I slot print_timing: id 1 | task 596 | n_gen = 135, tg = 4.35 t/s, tg_3s = 4.76 t/s 7.57.274.761 I slot print_timing: id 3 | task 519 | n_gen = 210, tg = 4.11 t/s, tg_3s = 4.76 t/s 8.00.426.690 I slot print_timing: id 0 | task 266 | n_gen = 470, tg = 4.21 t/s, tg_3s = 4.76 t/s 8.00.426.830 I slot print_timing: id 1 | task 596 | n_gen = 150, tg = 4.39 t/s, tg_3s = 4.76 t/s 8.00.427.105 I slot print_timing: id 3 | task 519 | n_gen = 225, tg = 4.14 t/s, tg_3s = 4.76 t/s 8.03.579.108 I slot print_timing: id 0 | task 266 | n_gen = 485, tg = 4.22 t/s, tg_3s = 4.76 t/s 8.03.579.252 I slot print_timing: id 1 | task 596 | n_gen = 165, tg = 4.42 t/s, tg_3s = 4.76 t/s 8.03.579.550 I slot print_timing: id 3 | task 519 | n_gen = 240, tg = 4.18 t/s, tg_3s = 4.76 t/s 8.06.733.361 I slot print_timing: id 0 | task 266 | n_gen = 500, tg = 4.24 t/s, tg_3s = 4.76 t/s 8.06.733.521 I slot print_timing: id 1 | task 596 | n_gen = 180, tg = 4.45 t/s, tg_3s = 4.76 t/s 8.06.733.798 I slot print_timing: id 3 | task 519 | n_gen = 255, tg = 4.21 t/s, tg_3s = 4.76 t/s 8.09.886.471 I slot print_timing: id 0 | task 266 | n_gen = 515, tg = 4.25 t/s, tg_3s = 4.76 t/s 8.09.886.613 I slot print_timing: id 1 | task 596 | n_gen = 195, tg = 4.47 t/s, tg_3s = 4.76 t/s 8.09.886.880 I slot print_timing: id 3 | task 519 | n_gen = 270, tg = 4.24 t/s, tg_3s = 4.76 t/s 8.12.410.633 I slot print_timing: id 2 | task 704 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.80 t/s 8.13.041.551 I slot print_timing: id 0 | task 266 | n_gen = 530, tg = 4.26 t/s, tg_3s = 4.75 t/s 8.13.041.696 I slot print_timing: id 1 | task 596 | n_gen = 210, tg = 4.49 t/s, tg_3s = 4.75 t/s 8.13.041.989 I slot print_timing: id 3 | task 519 | n_gen = 285, tg = 4.26 t/s, tg_3s = 4.75 t/s 8.15.565.988 I slot print_timing: id 2 | task 704 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.75 t/s 8.16.196.617 I slot print_timing: id 0 | task 266 | n_gen = 545, tg = 4.27 t/s, tg_3s = 4.75 t/s 8.16.196.767 I slot print_timing: id 1 | task 596 | n_gen = 225, tg = 4.51 t/s, tg_3s = 4.75 t/s 8.16.197.043 I slot print_timing: id 3 | task 519 | n_gen = 300, tg = 4.28 t/s, tg_3s = 4.75 t/s 8.18.723.967 I slot print_timing: id 2 | task 704 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.75 t/s 8.19.354.959 I slot print_timing: id 0 | task 266 | n_gen = 560, tg = 4.29 t/s, tg_3s = 4.75 t/s 8.19.355.111 I slot print_timing: id 1 | task 596 | n_gen = 240, tg = 4.52 t/s, tg_3s = 4.75 t/s 8.19.355.396 I slot print_timing: id 3 | task 519 | n_gen = 315, tg = 4.30 t/s, tg_3s = 4.75 t/s 8.20.196.689 I slot print_timing: id 1 | task 596 | prompt eval time = 2758.45 ms / 141 tokens ( 19.56 ms per token, 51.12 tokens per second) 8.20.196.691 I slot print_timing: id 1 | task 596 | eval time = 53714.29 ms / 244 tokens ( 221.05 ms per token, 4.52 tokens per second) 8.20.196.692 I slot print_timing: id 1 | task 596 | total time = 56472.74 ms / 385 tokens 8.20.196.692 I slot print_timing: id 1 | task 596 | graphs reused = 538 8.20.196.693 I slot print_timing: id 1 | task 596 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.196.736 I slot release: id 1 | task 596 | stop processing: n_tokens = 1509, truncated = 0 8.20.482.843 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.759 8.20.482.890 I slot launch_slot_: id 1 | task 844 | processing task, is_child = 0 8.22.343.939 I slot print_timing: id 2 | task 704 | n_gen = 139, tg = 4.49 t/s, tg_3s = 2.49 t/s 8.22.891.650 I slot print_timing: id 0 | task 266 | n_gen = 567, tg = 4.23 t/s, tg_3s = 1.98 t/s 8.22.892.175 I slot print_timing: id 3 | task 519 | n_gen = 322, tg = 4.19 t/s, tg_3s = 1.98 t/s 8.25.418.594 I slot print_timing: id 2 | task 704 | n_gen = 152, tg = 4.46 t/s, tg_3s = 4.23 t/s 8.25.629.058 I slot print_timing: id 3 | task 519 | prompt eval time = 2452.65 ms / 139 tokens ( 17.64 ms per token, 56.67 tokens per second) 8.25.629.062 I slot print_timing: id 3 | task 519 | eval time = 79257.74 ms / 335 tokens ( 237.30 ms per token, 4.21 tokens per second) 8.25.629.062 I slot print_timing: id 3 | task 519 | total time = 81710.38 ms / 474 tokens 8.25.629.063 I slot print_timing: id 3 | task 519 | graphs reused = 550 8.25.629.063 I slot print_timing: id 3 | task 519 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.629.115 I slot release: id 3 | task 519 | stop processing: n_tokens = 1598, truncated = 0 8.25.827.987 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.717 8.25.828.019 I slot launch_slot_: id 3 | task 861 | processing task, is_child = 0 8.27.195.574 I slot print_timing: id 0 | task 266 | n_gen = 582, tg = 4.20 t/s, tg_3s = 3.49 t/s 8.28.436.032 I slot print_timing: id 2 | task 704 | n_gen = 160, tg = 4.32 t/s, tg_3s = 2.65 t/s 8.29.907.669 I slot print_timing: id 0 | task 266 | prompt eval time = 58217.66 ms / 1243 tokens ( 46.84 ms per token, 21.35 tokens per second) 8.29.907.674 I slot print_timing: id 0 | task 266 | eval time = 140979.97 ms / 594 tokens ( 237.74 ms per token, 4.21 tokens per second) 8.29.907.675 I slot print_timing: id 0 | task 266 | total time = 199197.63 ms / 1837 tokens 8.29.907.675 I slot print_timing: id 0 | task 266 | graphs reused = 560 8.29.907.676 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.907.718 I slot release: id 0 | task 266 | stop processing: n_tokens = 1836, truncated = 0 8.30.106.950 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.624 8.30.106.986 I slot launch_slot_: id 0 | task 876 | processing task, is_child = 0 8.31.781.282 I slot print_timing: id 2 | task 704 | n_gen = 169, tg = 4.18 t/s, tg_3s = 2.69 t/s 8.34.899.492 I slot print_timing: id 2 | task 704 | n_gen = 183, tg = 4.20 t/s, tg_3s = 4.49 t/s 8.38.047.765 I slot print_timing: id 2 | task 704 | n_gen = 198, tg = 4.24 t/s, tg_3s = 4.76 t/s 8.41.197.780 I slot print_timing: id 2 | task 704 | n_gen = 213, tg = 4.27 t/s, tg_3s = 4.76 t/s 8.44.347.358 I slot print_timing: id 2 | task 704 | n_gen = 228, tg = 4.30 t/s, tg_3s = 4.76 t/s 8.46.657.720 I slot print_timing: id 1 | task 844 | n_gen = 100, tg = 4.17 t/s, tg_3s = 4.21 t/s 8.47.498.397 I slot print_timing: id 2 | task 704 | n_gen = 243, tg = 4.33 t/s, tg_3s = 4.76 t/s 8.47.711.113 I slot print_timing: id 3 | task 861 | prompt eval time = 1765.14 ms / 101 tokens ( 17.48 ms per token, 57.22 tokens per second) 8.47.711.116 I slot print_timing: id 3 | task 861 | eval time = 20117.95 ms / 89 tokens ( 228.61 ms per token, 4.37 tokens per second) 8.47.711.116 I slot print_timing: id 3 | task 861 | total time = 21883.09 ms / 190 tokens 8.47.711.117 I slot print_timing: id 3 | task 861 | graphs reused = 633 8.47.711.117 I slot print_timing: id 3 | task 861 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.711.164 I slot release: id 3 | task 861 | stop processing: n_tokens = 1314, truncated = 0 8.47.909.897 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.872 8.47.909.929 I slot launch_slot_: id 3 | task 954 | processing task, is_child = 0 8.49.679.493 I slot print_timing: id 1 | task 844 | n_gen = 108, tg = 3.99 t/s, tg_3s = 2.65 t/s 8.50.521.729 I slot print_timing: id 2 | task 704 | n_gen = 251, tg = 4.24 t/s, tg_3s = 2.65 t/s 8.50.731.835 I slot print_timing: id 1 | task 844 | prompt eval time = 2408.95 ms / 125 tokens ( 19.27 ms per token, 51.89 tokens per second) 8.50.731.840 I slot print_timing: id 1 | task 844 | eval time = 27839.99 ms / 113 tokens ( 248.57 ms per token, 4.02 tokens per second) 8.50.731.841 I slot print_timing: id 1 | task 844 | total time = 30248.94 ms / 238 tokens 8.50.731.841 I slot print_timing: id 1 | task 844 | graphs reused = 637 8.50.731.842 I slot print_timing: id 1 | task 844 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.731.888 I slot release: id 1 | task 844 | stop processing: n_tokens = 1362, truncated = 0 8.51.017.154 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.841 8.51.017.191 I slot launch_slot_: id 1 | task 963 | processing task, is_child = 0 8.53.638.210 I slot print_timing: id 2 | task 704 | n_gen = 256, tg = 4.11 t/s, tg_3s = 1.60 t/s 8.56.368.230 I slot print_timing: id 0 | task 876 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 8.56.788.839 I slot print_timing: id 2 | task 704 | n_gen = 271, tg = 4.14 t/s, tg_3s = 4.76 t/s 8.56.998.538 I slot print_timing: id 2 | task 704 | prompt eval time = 2979.08 ms / 169 tokens ( 17.63 ms per token, 56.73 tokens per second) 8.56.998.544 I slot print_timing: id 2 | task 704 | eval time = 65400.95 ms / 272 tokens ( 241.33 ms per token, 4.14 tokens per second) 8.56.998.544 I slot print_timing: id 2 | task 704 | total time = 68380.03 ms / 441 tokens 8.56.998.544 I slot print_timing: id 2 | task 704 | graphs reused = 653 8.56.998.545 I slot print_timing: id 2 | task 704 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.998.591 I slot release: id 2 | task 704 | stop processing: n_tokens = 1565, truncated = 0 8.57.283.505 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.732 8.57.283.550 I slot launch_slot_: id 2 | task 984 | processing task, is_child = 0 8.59.433.072 I slot print_timing: id 0 | task 876 | n_gen = 105, tg = 3.81 t/s, tg_3s = 1.63 t/s 9.02.436.105 I slot print_timing: id 0 | task 876 | n_gen = 118, tg = 3.87 t/s, tg_3s = 4.33 t/s 9.05.585.479 I slot print_timing: id 0 | task 876 | n_gen = 133, tg = 3.95 t/s, tg_3s = 4.76 t/s 9.08.733.051 I slot print_timing: id 0 | task 876 | n_gen = 148, tg = 4.02 t/s, tg_3s = 4.77 t/s 9.11.880.952 I slot print_timing: id 0 | task 876 | prompt eval time = 2060.54 ms / 101 tokens ( 20.40 ms per token, 49.02 tokens per second) 9.11.880.957 I slot print_timing: id 0 | task 876 | eval time = 39713.42 ms / 163 tokens ( 245.14 ms per token, 4.08 tokens per second) 9.11.880.957 I slot print_timing: id 0 | task 876 | total time = 41773.96 ms / 264 tokens 9.11.880.958 I slot print_timing: id 0 | task 876 | graphs reused = 709 9.11.880.958 I slot print_timing: id 0 | task 876 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.880.999 I slot release: id 0 | task 876 | stop processing: n_tokens = 1388, truncated = 0 9.12.079.836 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.826 9.12.079.871 I slot launch_slot_: id 0 | task 1045 | processing task, is_child = 0 9.16.126.861 I slot print_timing: id 3 | task 954 | n_gen = 100, tg = 3.74 t/s, tg_3s = 3.78 t/s 9.17.805.777 I slot print_timing: id 1 | task 963 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.10 t/s 9.19.274.936 I slot print_timing: id 3 | task 954 | n_gen = 115, tg = 3.85 t/s, tg_3s = 4.76 t/s 9.20.952.226 I slot print_timing: id 1 | task 963 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.77 t/s 9.22.001.924 I slot print_timing: id 2 | task 984 | n_gen = 100, tg = 4.48 t/s, tg_3s = 4.53 t/s 9.22.421.882 I slot print_timing: id 3 | task 954 | n_gen = 130, tg = 3.94 t/s, tg_3s = 4.77 t/s 9.24.099.850 I slot print_timing: id 1 | task 963 | n_gen = 130, tg = 4.21 t/s, tg_3s = 4.77 t/s 9.25.149.518 I slot print_timing: id 2 | task 984 | n_gen = 115, tg = 4.52 t/s, tg_3s = 4.77 t/s 9.25.569.561 I slot print_timing: id 3 | task 954 | n_gen = 145, tg = 4.01 t/s, tg_3s = 4.77 t/s 9.27.248.267 I slot print_timing: id 1 | task 963 | n_gen = 145, tg = 4.26 t/s, tg_3s = 4.76 t/s 9.28.297.599 I slot print_timing: id 2 | task 984 | n_gen = 130, tg = 4.55 t/s, tg_3s = 4.76 t/s 9.28.717.566 I slot print_timing: id 3 | task 954 | n_gen = 160, tg = 4.07 t/s, tg_3s = 4.76 t/s 9.29.976.143 I slot print_timing: id 1 | task 963 | prompt eval time = 2408.54 ms / 120 tokens ( 20.07 ms per token, 49.82 tokens per second) 9.29.976.146 I slot print_timing: id 1 | task 963 | eval time = 36550.40 ms / 158 tokens ( 232.81 ms per token, 4.30 tokens per second) 9.29.976.147 I slot print_timing: id 1 | task 963 | total time = 38958.94 ms / 278 tokens 9.29.976.148 I slot print_timing: id 1 | task 963 | graphs reused = 786 9.29.976.148 I slot print_timing: id 1 | task 963 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.976.199 I slot release: id 1 | task 963 | stop processing: n_tokens = 1402, truncated = 0 9.30.261.448 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.817 9.30.261.484 I slot launch_slot_: id 1 | task 1126 | processing task, is_child = 0 9.32.120.577 I slot print_timing: id 2 | task 984 | n_gen = 140, tg = 4.32 t/s, tg_3s = 2.62 t/s 9.32.120.786 I slot print_timing: id 3 | task 954 | n_gen = 168, tg = 3.93 t/s, tg_3s = 2.35 t/s 9.35.189.196 I slot print_timing: id 2 | task 984 | n_gen = 153, tg = 4.31 t/s, tg_3s = 4.24 t/s 9.35.189.346 I slot print_timing: id 3 | task 954 | n_gen = 181, tg = 3.96 t/s, tg_3s = 4.24 t/s 9.36.658.130 I slot print_timing: id 0 | task 1045 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.38 t/s 9.38.336.623 I slot print_timing: id 2 | task 984 | n_gen = 168, tg = 4.35 t/s, tg_3s = 4.77 t/s 9.38.336.777 I slot print_timing: id 3 | task 954 | n_gen = 196, tg = 4.01 t/s, tg_3s = 4.77 t/s 9.38.546.495 I slot print_timing: id 0 | task 1045 | prompt eval time = 1736.65 ms / 86 tokens ( 20.19 ms per token, 49.52 tokens per second) 9.38.546.500 I slot print_timing: id 0 | task 1045 | eval time = 24729.97 ms / 109 tokens ( 228.98 ms per token, 4.37 tokens per second) 9.38.546.500 I slot print_timing: id 0 | task 1045 | total time = 26466.62 ms / 195 tokens 9.38.546.501 I slot print_timing: id 0 | task 1045 | graphs reused = 813 9.38.546.501 I slot print_timing: id 0 | task 1045 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.546.545 I slot release: id 0 | task 1045 | stop processing: n_tokens = 1319, truncated = 0 9.38.746.345 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.869 9.38.746.375 I slot launch_slot_: id 0 | task 1158 | processing task, is_child = 0 9.41.544.496 I slot print_timing: id 2 | task 984 | n_gen = 177, tg = 4.23 t/s, tg_3s = 2.81 t/s 9.41.544.644 I slot print_timing: id 3 | task 954 | n_gen = 205, tg = 3.93 t/s, tg_3s = 2.81 t/s 9.44.692.508 I slot print_timing: id 2 | task 984 | n_gen = 192, tg = 4.27 t/s, tg_3s = 4.76 t/s 9.44.692.670 I slot print_timing: id 3 | task 954 | n_gen = 220, tg = 3.98 t/s, tg_3s = 4.76 t/s 9.47.842.271 I slot print_timing: id 2 | task 984 | n_gen = 207, tg = 4.30 t/s, tg_3s = 4.76 t/s 9.47.842.415 I slot print_timing: id 3 | task 954 | n_gen = 235, tg = 4.02 t/s, tg_3s = 4.76 t/s 9.50.989.978 I slot print_timing: id 2 | task 984 | n_gen = 222, tg = 4.33 t/s, tg_3s = 4.77 t/s 9.50.990.135 I slot print_timing: id 3 | task 954 | n_gen = 250, tg = 4.06 t/s, tg_3s = 4.77 t/s 9.54.138.814 I slot print_timing: id 2 | task 984 | n_gen = 237, tg = 4.35 t/s, tg_3s = 4.76 t/s 9.54.138.982 I slot print_timing: id 3 | task 954 | n_gen = 265, tg = 4.10 t/s, tg_3s = 4.76 t/s 9.54.348.803 I slot print_timing: id 0 | task 1158 | prompt eval time = 1746.34 ms / 97 tokens ( 18.00 ms per token, 55.54 tokens per second) 9.54.348.808 I slot print_timing: id 0 | task 1158 | eval time = 13856.08 ms / 67 tokens ( 209.94 ms per token, 4.76 tokens per second) 9.54.348.809 I slot print_timing: id 0 | task 1158 | total time = 15602.42 ms / 164 tokens 9.54.348.810 I slot print_timing: id 0 | task 1158 | graphs reused = 879 9.54.348.810 I slot print_timing: id 0 | task 1158 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.348.858 I slot release: id 0 | task 1158 | stop processing: n_tokens = 1288, truncated = 0 9.54.548.928 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.890 9.54.548.969 I slot launch_slot_: id 0 | task 1228 | processing task, is_child = 0 9.55.895.697 I slot print_timing: id 1 | task 1126 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.31 t/s 9.57.332.371 I slot print_timing: id 2 | task 984 | n_gen = 246, tg = 4.27 t/s, tg_3s = 2.82 t/s 9.57.332.521 I slot print_timing: id 3 | task 954 | n_gen = 274, tg = 4.04 t/s, tg_3s = 2.82 t/s 9.59.011.676 I slot print_timing: id 1 | task 1126 | n_gen = 114, tg = 4.29 t/s, tg_3s = 4.49 t/s 10.00.481.214 I slot print_timing: id 2 | task 984 | n_gen = 261, tg = 4.29 t/s, tg_3s = 4.76 t/s 10.00.481.377 I slot print_timing: id 3 | task 954 | n_gen = 289, tg = 4.07 t/s, tg_3s = 4.76 t/s 10.02.164.232 I slot print_timing: id 1 | task 1126 | n_gen = 129, tg = 4.34 t/s, tg_3s = 4.76 t/s 10.03.634.560 I slot print_timing: id 2 | task 984 | n_gen = 276, tg = 4.32 t/s, tg_3s = 4.76 t/s 10.03.634.715 I slot print_timing: id 3 | task 954 | n_gen = 304, tg = 4.10 t/s, tg_3s = 4.76 t/s 10.05.314.199 I slot print_timing: id 1 | task 1126 | n_gen = 144, tg = 4.38 t/s, tg_3s = 4.76 t/s 10.06.784.416 I slot print_timing: id 2 | task 984 | n_gen = 291, tg = 4.34 t/s, tg_3s = 4.76 t/s 10.06.784.566 I slot print_timing: id 3 | task 954 | n_gen = 319, tg = 4.12 t/s, tg_3s = 4.76 t/s 10.08.255.159 I slot print_timing: id 3 | task 954 | prompt eval time = 1769.88 ms / 95 tokens ( 18.63 ms per token, 53.68 tokens per second) 10.08.255.165 I slot print_timing: id 3 | task 954 | eval time = 78575.34 ms / 326 tokens ( 241.77 ms per token, 4.14 tokens per second) 10.08.255.165 I slot print_timing: id 3 | task 954 | total time = 80345.22 ms / 421 tokens 10.08.255.166 I slot print_timing: id 3 | task 954 | graphs reused = 935 10.08.255.166 I slot print_timing: id 3 | task 954 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.255.215 I slot release: id 3 | task 954 | stop processing: n_tokens = 1545, truncated = 0 10.08.453.967 I slot print_timing: id 1 | task 1126 | n_gen = 159, tg = 4.42 t/s, tg_3s = 4.78 t/s 10.08.454.125 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.742 10.08.454.151 I slot launch_slot_: id 3 | task 1289 | processing task, is_child = 0 10.09.820.164 I slot print_timing: id 2 | task 984 | n_gen = 300, tg = 4.28 t/s, tg_3s = 2.96 t/s 10.11.475.867 I slot print_timing: id 1 | task 1126 | n_gen = 167, tg = 4.28 t/s, tg_3s = 2.65 t/s 10.12.945.636 I slot print_timing: id 2 | task 984 | n_gen = 314, tg = 4.29 t/s, tg_3s = 4.48 t/s 10.14.204.350 I slot print_timing: id 0 | task 1228 | prompt eval time = 1731.21 ms / 84 tokens ( 20.61 ms per token, 48.52 tokens per second) 10.14.204.355 I slot print_timing: id 0 | task 1228 | eval time = 17924.16 ms / 80 tokens ( 226.89 ms per token, 4.41 tokens per second) 10.14.204.355 I slot print_timing: id 0 | task 1228 | total time = 19655.37 ms / 164 tokens 10.14.204.356 I slot print_timing: id 0 | task 1228 | graphs reused = 953 10.14.204.356 I slot print_timing: id 0 | task 1228 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.204.400 I slot release: id 0 | task 1228 | stop processing: n_tokens = 1288, truncated = 0 10.14.403.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.890 10.14.403.793 I slot launch_slot_: id 0 | task 1312 | processing task, is_child = 0 10.15.763.789 I slot print_timing: id 1 | task 1126 | n_gen = 182, tg = 4.20 t/s, tg_3s = 3.50 t/s 10.16.150.027 I slot print_timing: id 2 | task 984 | n_gen = 323, tg = 4.22 t/s, tg_3s = 2.81 t/s 10.18.882.929 I slot print_timing: id 1 | task 1126 | n_gen = 196, tg = 4.22 t/s, tg_3s = 4.49 t/s 10.19.302.536 I slot print_timing: id 2 | task 984 | n_gen = 338, tg = 4.25 t/s, tg_3s = 4.76 t/s 10.22.032.696 I slot print_timing: id 1 | task 1126 | n_gen = 211, tg = 4.25 t/s, tg_3s = 4.76 t/s 10.22.452.860 I slot print_timing: id 2 | task 984 | n_gen = 353, tg = 4.26 t/s, tg_3s = 4.76 t/s 10.25.183.037 I slot print_timing: id 1 | task 1126 | n_gen = 226, tg = 4.28 t/s, tg_3s = 4.76 t/s 10.25.603.521 I slot print_timing: id 2 | task 984 | n_gen = 368, tg = 4.28 t/s, tg_3s = 4.76 t/s 10.28.333.232 I slot print_timing: id 1 | task 1126 | n_gen = 241, tg = 4.31 t/s, tg_3s = 4.76 t/s 10.28.753.658 I slot print_timing: id 2 | task 984 | n_gen = 383, tg = 4.30 t/s, tg_3s = 4.76 t/s 10.29.803.138 I slot print_timing: id 0 | task 1312 | prompt eval time = 1745.95 ms / 95 tokens ( 18.38 ms per token, 54.41 tokens per second) 10.29.803.140 I slot print_timing: id 0 | task 1312 | eval time = 13653.39 ms / 66 tokens ( 210.05 ms per token, 4.76 tokens per second) 10.29.803.141 I slot print_timing: id 0 | task 1312 | total time = 15399.34 ms / 161 tokens 10.29.803.141 I slot print_timing: id 0 | task 1312 | graphs reused = 1018 10.29.803.142 I slot print_timing: id 0 | task 1312 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.803.186 I slot release: id 0 | task 1312 | stop processing: n_tokens = 1285, truncated = 0 10.30.002.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.892 10.30.002.563 I slot launch_slot_: id 0 | task 1381 | processing task, is_child = 0 10.31.701.917 I slot print_timing: id 1 | task 1126 | n_gen = 250, tg = 4.22 t/s, tg_3s = 2.67 t/s 10.32.087.593 I slot print_timing: id 2 | task 984 | n_gen = 391, tg = 4.23 t/s, tg_3s = 2.40 t/s 10.32.720.217 I slot print_timing: id 2 | task 984 | prompt eval time = 2631.49 ms / 148 tokens ( 17.78 ms per token, 56.24 tokens per second) 10.32.720.222 I slot print_timing: id 2 | task 984 | eval time = 92805.17 ms / 394 tokens ( 236.15 ms per token, 4.23 tokens per second) 10.32.720.223 I slot print_timing: id 2 | task 984 | total time = 95436.66 ms / 542 tokens 10.32.720.223 I slot print_timing: id 2 | task 984 | graphs reused = 1021 10.32.720.224 I slot print_timing: id 2 | task 984 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.720.272 I slot release: id 2 | task 984 | stop processing: n_tokens = 1666, truncated = 0 10.33.005.659 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.688 10.33.005.708 I slot launch_slot_: id 2 | task 1388 | processing task, is_child = 0 10.34.944.175 I slot print_timing: id 1 | task 1126 | n_gen = 257, tg = 4.11 t/s, tg_3s = 2.16 t/s 10.35.576.778 I slot print_timing: id 3 | task 1289 | n_gen = 100, tg = 3.90 t/s, tg_3s = 3.94 t/s 10.36.836.207 I slot print_timing: id 1 | task 1126 | prompt eval time = 2407.36 ms / 133 tokens ( 18.10 ms per token, 55.25 tokens per second) 10.36.836.210 I slot print_timing: id 1 | task 1126 | eval time = 64167.35 ms / 266 tokens ( 242.14 ms per token, 4.13 tokens per second) 10.36.836.210 I slot print_timing: id 1 | task 1126 | total time = 66574.71 ms / 399 tokens 10.36.836.211 I slot print_timing: id 1 | task 1126 | graphs reused = 1029 10.36.836.211 I slot print_timing: id 1 | task 1126 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.836.256 I slot release: id 1 | task 1126 | stop processing: n_tokens = 1523, truncated = 0 10.37.121.168 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.752 10.37.121.206 I slot launch_slot_: id 1 | task 1401 | processing task, is_child = 0 10.38.646.106 I slot print_timing: id 3 | task 1289 | n_gen = 108, tg = 3.76 t/s, tg_3s = 2.61 t/s 10.41.712.625 I slot print_timing: id 3 | task 1289 | n_gen = 121, tg = 3.81 t/s, tg_3s = 4.24 t/s 10.44.859.846 I slot print_timing: id 3 | task 1289 | n_gen = 136, tg = 3.90 t/s, tg_3s = 4.77 t/s 10.48.007.535 I slot print_timing: id 3 | task 1289 | n_gen = 151, tg = 3.97 t/s, tg_3s = 4.77 t/s 10.51.154.861 I slot print_timing: id 3 | task 1289 | n_gen = 166, tg = 4.03 t/s, tg_3s = 4.77 t/s 10.54.302.829 I slot print_timing: id 3 | task 1289 | n_gen = 181, tg = 4.08 t/s, tg_3s = 4.76 t/s 10.56.192.053 I slot print_timing: id 0 | task 1381 | n_gen = 100, tg = 4.11 t/s, tg_3s = 4.15 t/s 10.57.451.449 I slot print_timing: id 2 | task 1388 | prompt eval time = 1938.68 ms / 90 tokens ( 21.54 ms per token, 46.42 tokens per second) 10.57.451.455 I slot print_timing: id 2 | task 1388 | eval time = 22507.06 ms / 100 tokens ( 227.34 ms per token, 4.40 tokens per second) 10.57.451.456 I slot print_timing: id 2 | task 1388 | total time = 24445.73 ms / 190 tokens 10.57.451.456 I slot print_timing: id 2 | task 1388 | graphs reused = 1115 10.57.451.456 I slot print_timing: id 2 | task 1388 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.451.499 I slot release: id 2 | task 1388 | stop processing: n_tokens = 1314, truncated = 0 10.57.451.648 I slot print_timing: id 3 | task 1289 | n_gen = 196, tg = 4.13 t/s, tg_3s = 4.76 t/s 10.57.737.002 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.872 10.57.737.040 I slot launch_slot_: id 2 | task 1492 | processing task, is_child = 0 10.59.672.405 I slot print_timing: id 0 | task 1381 | n_gen = 109, tg = 3.92 t/s, tg_3s = 2.59 t/s 11.00.514.807 I slot print_timing: id 3 | task 1289 | n_gen = 203, tg = 4.02 t/s, tg_3s = 2.29 t/s 11.01.564.614 I slot print_timing: id 1 | task 1401 | n_gen = 100, tg = 4.43 t/s, tg_3s = 4.47 t/s 11.02.824.265 I slot print_timing: id 0 | task 1381 | n_gen = 124, tg = 4.00 t/s, tg_3s = 4.76 t/s 11.03.664.367 I slot print_timing: id 3 | task 1289 | n_gen = 218, tg = 4.06 t/s, tg_3s = 4.76 t/s 11.03.874.102 I slot print_timing: id 1 | task 1401 | prompt eval time = 2071.81 ms / 96 tokens ( 21.58 ms per token, 46.34 tokens per second) 11.03.874.107 I slot print_timing: id 1 | task 1401 | eval time = 24681.08 ms / 111 tokens ( 224.37 ms per token, 4.46 tokens per second) 11.03.874.108 I slot print_timing: id 1 | task 1401 | total time = 26752.89 ms / 207 tokens 11.03.874.108 I slot print_timing: id 1 | task 1401 | graphs reused = 1134 11.03.874.109 I slot print_timing: id 1 | task 1401 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.874.155 I slot release: id 1 | task 1401 | stop processing: n_tokens = 1331, truncated = 0 11.04.159.854 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.861 11.04.159.889 I slot launch_slot_: id 1 | task 1516 | processing task, is_child = 0 11.06.030.269 I slot print_timing: id 0 | task 1381 | n_gen = 131, tg = 3.83 t/s, tg_3s = 2.18 t/s 11.06.792.351 I slot print_timing: id 3 | task 1289 | n_gen = 223, tg = 3.92 t/s, tg_3s = 1.60 t/s 11.09.101.797 I slot print_timing: id 0 | task 1381 | n_gen = 144, tg = 3.86 t/s, tg_3s = 4.23 t/s 11.09.942.339 I slot print_timing: id 3 | task 1289 | n_gen = 238, tg = 3.97 t/s, tg_3s = 4.76 t/s 11.10.991.927 I slot print_timing: id 3 | task 1289 | prompt eval time = 1760.13 ms / 101 tokens ( 17.43 ms per token, 57.38 tokens per second) 11.10.991.929 I slot print_timing: id 3 | task 1289 | eval time = 60777.63 ms / 243 tokens ( 251.15 ms per token, 3.98 tokens per second) 11.10.991.930 I slot print_timing: id 3 | task 1289 | total time = 62537.77 ms / 344 tokens 11.10.991.930 I slot print_timing: id 3 | task 1289 | graphs reused = 1154 11.10.991.931 I slot print_timing: id 3 | task 1289 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.991.974 I slot release: id 3 | task 1289 | stop processing: n_tokens = 1468, truncated = 0 11.11.190.536 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.781 11.11.190.566 I slot launch_slot_: id 3 | task 1541 | processing task, is_child = 0 11.13.244.565 I slot print_timing: id 0 | task 1381 | n_gen = 155, tg = 3.74 t/s, tg_3s = 2.66 t/s 11.16.373.829 I slot print_timing: id 0 | task 1381 | n_gen = 169, tg = 3.79 t/s, tg_3s = 4.47 t/s 11.19.522.437 I slot print_timing: id 0 | task 1381 | n_gen = 184, tg = 3.86 t/s, tg_3s = 4.76 t/s 11.22.672.668 I slot print_timing: id 0 | task 1381 | n_gen = 199, tg = 3.91 t/s, tg_3s = 4.76 t/s 11.24.562.530 I slot print_timing: id 2 | task 1492 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 11.25.822.590 I slot print_timing: id 0 | task 1381 | n_gen = 214, tg = 3.96 t/s, tg_3s = 4.76 t/s 11.27.712.935 I slot print_timing: id 2 | task 1492 | n_gen = 115, tg = 4.07 t/s, tg_3s = 4.76 t/s 11.28.973.518 I slot print_timing: id 0 | task 1381 | n_gen = 229, tg = 4.01 t/s, tg_3s = 4.76 t/s 11.29.394.099 I slot print_timing: id 1 | task 1516 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 11.30.863.942 I slot print_timing: id 2 | task 1492 | n_gen = 130, tg = 4.14 t/s, tg_3s = 4.76 t/s 11.31.073.925 I slot print_timing: id 2 | task 1492 | prompt eval time = 1935.75 ms / 87 tokens ( 22.25 ms per token, 44.94 tokens per second) 11.31.073.930 I slot print_timing: id 2 | task 1492 | eval time = 31401.13 ms / 131 tokens ( 241.55 ms per token, 4.14 tokens per second) 11.31.073.931 I slot print_timing: id 2 | task 1492 | total time = 33336.88 ms / 218 tokens 11.31.073.931 I slot print_timing: id 2 | task 1492 | graphs reused = 1236 11.31.073.932 I slot print_timing: id 2 | task 1492 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.073.975 I slot release: id 2 | task 1492 | stop processing: n_tokens = 1342, truncated = 0 11.31.359.588 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.854 11.31.359.622 I slot launch_slot_: id 2 | task 1628 | processing task, is_child = 0 11.33.512.941 I slot print_timing: id 0 | task 1381 | n_gen = 241, tg = 3.91 t/s, tg_3s = 2.64 t/s 11.33.513.100 I slot print_timing: id 1 | task 1516 | n_gen = 110, tg = 4.05 t/s, tg_3s = 2.43 t/s 11.36.520.148 I slot print_timing: id 0 | task 1381 | n_gen = 254, tg = 3.93 t/s, tg_3s = 4.32 t/s 11.36.520.290 I slot print_timing: id 1 | task 1516 | n_gen = 123, tg = 4.07 t/s, tg_3s = 4.32 t/s 11.36.730.722 I slot print_timing: id 3 | task 1541 | n_gen = 100, tg = 4.29 t/s, tg_3s = 4.33 t/s 11.39.672.297 I slot print_timing: id 0 | task 1381 | n_gen = 269, tg = 3.97 t/s, tg_3s = 4.76 t/s 11.39.672.443 I slot print_timing: id 1 | task 1516 | n_gen = 138, tg = 4.14 t/s, tg_3s = 4.76 t/s 11.39.882.782 I slot print_timing: id 3 | task 1541 | n_gen = 115, tg = 4.34 t/s, tg_3s = 4.76 t/s 11.42.825.958 I slot print_timing: id 0 | task 1381 | n_gen = 284, tg = 4.00 t/s, tg_3s = 4.76 t/s 11.42.826.110 I slot print_timing: id 1 | task 1516 | n_gen = 153, tg = 4.19 t/s, tg_3s = 4.76 t/s 11.43.036.582 I slot print_timing: id 3 | task 1541 | n_gen = 130, tg = 4.39 t/s, tg_3s = 4.76 t/s 11.45.978.368 I slot print_timing: id 0 | task 1381 | n_gen = 299, tg = 4.03 t/s, tg_3s = 4.76 t/s 11.45.978.515 I slot print_timing: id 1 | task 1516 | n_gen = 168, tg = 4.24 t/s, tg_3s = 4.76 t/s 11.46.188.949 I slot print_timing: id 3 | task 1541 | n_gen = 145, tg = 4.42 t/s, tg_3s = 4.76 t/s 11.49.130.767 I slot print_timing: id 0 | task 1381 | n_gen = 314, tg = 4.06 t/s, tg_3s = 4.76 t/s 11.49.130.911 I slot print_timing: id 1 | task 1516 | n_gen = 183, tg = 4.28 t/s, tg_3s = 4.76 t/s 11.49.341.367 I slot print_timing: id 3 | task 1541 | n_gen = 160, tg = 4.45 t/s, tg_3s = 4.76 t/s 11.51.652.469 I slot print_timing: id 0 | task 1381 | prompt eval time = 2084.74 ms / 130 tokens ( 16.04 ms per token, 62.36 tokens per second) 11.51.652.474 I slot print_timing: id 0 | task 1381 | eval time = 79565.16 ms / 326 tokens ( 244.82 ms per token, 4.08 tokens per second) 11.51.652.475 I slot print_timing: id 0 | task 1381 | total time = 81649.90 ms / 456 tokens 11.51.652.475 I slot print_timing: id 0 | task 1381 | graphs reused = 1318 11.51.652.476 I slot print_timing: id 0 | task 1381 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.652.523 I slot release: id 0 | task 1381 | stop processing: n_tokens = 1580, truncated = 0 11.51.851.943 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.725 11.51.851.980 I slot launch_slot_: id 0 | task 1716 | processing task, is_child = 0 11.53.210.336 I slot print_timing: id 1 | task 1516 | n_gen = 197, tg = 4.20 t/s, tg_3s = 3.43 t/s 11.53.210.636 I slot print_timing: id 3 | task 1541 | n_gen = 173, tg = 4.35 t/s, tg_3s = 3.36 t/s 11.56.119.271 I slot print_timing: id 2 | task 1628 | n_gen = 100, tg = 4.48 t/s, tg_3s = 4.52 t/s 11.56.329.035 I slot print_timing: id 1 | task 1516 | n_gen = 211, tg = 4.22 t/s, tg_3s = 4.49 t/s 11.56.329.323 I slot print_timing: id 3 | task 1541 | n_gen = 187, tg = 4.36 t/s, tg_3s = 4.49 t/s 11.59.269.615 I slot print_timing: id 2 | task 1628 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.76 t/s 11.59.479.569 I slot print_timing: id 1 | task 1516 | n_gen = 226, tg = 4.25 t/s, tg_3s = 4.76 t/s 11.59.479.844 I slot print_timing: id 3 | task 1541 | n_gen = 202, tg = 4.39 t/s, tg_3s = 4.76 t/s 12.02.419.638 I slot print_timing: id 2 | task 1628 | n_gen = 130, tg = 4.54 t/s, tg_3s = 4.76 t/s 12.02.629.848 I slot print_timing: id 1 | task 1516 | n_gen = 241, tg = 4.28 t/s, tg_3s = 4.76 t/s 12.02.630.125 I slot print_timing: id 3 | task 1541 | n_gen = 217, tg = 4.41 t/s, tg_3s = 4.76 t/s 12.05.572.308 I slot print_timing: id 2 | task 1628 | n_gen = 145, tg = 4.56 t/s, tg_3s = 4.76 t/s 12.05.782.279 I slot print_timing: id 1 | task 1516 | n_gen = 256, tg = 4.31 t/s, tg_3s = 4.76 t/s 12.05.782.556 I slot print_timing: id 3 | task 1541 | n_gen = 232, tg = 4.43 t/s, tg_3s = 4.76 t/s 12.08.303.846 I slot print_timing: id 0 | task 1716 | prompt eval time = 1744.97 ms / 93 tokens ( 18.76 ms per token, 53.30 tokens per second) 12.08.303.849 I slot print_timing: id 0 | task 1716 | eval time = 14706.89 ms / 71 tokens ( 210.10 ms per token, 4.76 tokens per second) 12.08.303.849 I slot print_timing: id 0 | task 1716 | total time = 16451.86 ms / 164 tokens 12.08.303.850 I slot print_timing: id 0 | task 1716 | graphs reused = 1388 12.08.303.850 I slot print_timing: id 0 | task 1716 | graph reallocs = 0 / 0 (same size) / (changed size) 12.08.303.896 I slot release: id 0 | task 1716 | stop processing: n_tokens = 1288, truncated = 0 12.08.503.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.890 12.08.503.532 I slot launch_slot_: id 0 | task 1790 | processing task, is_child = 0 12.09.856.441 I slot print_timing: id 1 | task 1516 | n_gen = 270, tg = 4.25 t/s, tg_3s = 3.44 t/s 12.09.856.595 I slot print_timing: id 2 | task 1628 | n_gen = 160, tg = 4.43 t/s, tg_3s = 3.50 t/s 12.09.856.759 I slot print_timing: id 3 | task 1541 | n_gen = 246, tg = 4.36 t/s, tg_3s = 3.44 t/s 12.12.978.801 I slot print_timing: id 1 | task 1516 | n_gen = 284, tg = 4.26 t/s, tg_3s = 4.48 t/s 12.12.978.953 I slot print_timing: id 2 | task 1628 | n_gen = 174, tg = 4.44 t/s, tg_3s = 4.48 t/s 12.12.979.128 I slot print_timing: id 3 | task 1541 | n_gen = 260, tg = 4.36 t/s, tg_3s = 4.48 t/s 12.16.129.995 I slot print_timing: id 1 | task 1516 | n_gen = 299, tg = 4.28 t/s, tg_3s = 4.76 t/s 12.16.130.145 I slot print_timing: id 2 | task 1628 | n_gen = 189, tg = 4.46 t/s, tg_3s = 4.76 t/s 12.16.130.296 I slot print_timing: id 3 | task 1541 | n_gen = 275, tg = 4.38 t/s, tg_3s = 4.76 t/s 12.19.281.593 I slot print_timing: id 1 | task 1516 | n_gen = 314, tg = 4.31 t/s, tg_3s = 4.76 t/s 12.19.281.753 I slot print_timing: id 2 | task 1628 | n_gen = 204, tg = 4.48 t/s, tg_3s = 4.76 t/s 12.19.281.900 I slot print_timing: id 3 | task 1541 | n_gen = 290, tg = 4.40 t/s, tg_3s = 4.76 t/s 12.22.433.220 I slot print_timing: id 0 | task 1790 | prompt eval time = 1738.62 ms / 87 tokens ( 19.98 ms per token, 50.04 tokens per second) 12.22.433.225 I slot print_timing: id 0 | task 1790 | eval time = 12191.06 ms / 59 tokens ( 210.19 ms per token, 4.76 tokens per second) 12.22.433.226 I slot print_timing: id 0 | task 1790 | total time = 13929.68 ms / 146 tokens 12.22.433.226 I slot print_timing: id 0 | task 1790 | graphs reused = 1445 12.22.433.227 I slot print_timing: id 0 | task 1790 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.433.274 I slot release: id 0 | task 1790 | stop processing: n_tokens = 1270, truncated = 0 12.22.433.422 I slot print_timing: id 1 | task 1516 | n_gen = 329, tg = 4.32 t/s, tg_3s = 4.76 t/s 12.22.433.586 I slot print_timing: id 2 | task 1628 | n_gen = 219, tg = 4.50 t/s, tg_3s = 4.76 t/s 12.22.433.752 I slot print_timing: id 3 | task 1541 | n_gen = 305, tg = 4.42 t/s, tg_3s = 4.76 t/s 12.22.632.857 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.902 12.22.632.887 I slot launch_slot_: id 0 | task 1852 | processing task, is_child = 0 12.25.436.956 I slot print_timing: id 1 | task 1516 | n_gen = 337, tg = 4.26 t/s, tg_3s = 2.66 t/s 12.25.437.109 I slot print_timing: id 2 | task 1628 | n_gen = 227, tg = 4.39 t/s, tg_3s = 2.66 t/s 12.25.437.260 I slot print_timing: id 3 | task 1541 | n_gen = 313, tg = 4.35 t/s, tg_3s = 2.66 t/s 12.28.589.521 I slot print_timing: id 1 | task 1516 | n_gen = 352, tg = 4.28 t/s, tg_3s = 4.76 t/s 12.28.589.668 I slot print_timing: id 2 | task 1628 | n_gen = 242, tg = 4.41 t/s, tg_3s = 4.76 t/s 12.28.589.826 I slot print_timing: id 3 | task 1541 | n_gen = 328, tg = 4.36 t/s, tg_3s = 4.76 t/s 12.31.741.995 I slot print_timing: id 1 | task 1516 | n_gen = 367, tg = 4.30 t/s, tg_3s = 4.76 t/s 12.31.742.144 I slot print_timing: id 2 | task 1628 | n_gen = 257, tg = 4.43 t/s, tg_3s = 4.76 t/s 12.31.742.294 I slot print_timing: id 3 | task 1541 | n_gen = 343, tg = 4.38 t/s, tg_3s = 4.76 t/s 12.34.896.178 I slot print_timing: id 1 | task 1516 | n_gen = 382, tg = 4.31 t/s, tg_3s = 4.76 t/s 12.34.896.334 I slot print_timing: id 2 | task 1628 | n_gen = 272, tg = 4.45 t/s, tg_3s = 4.76 t/s 12.34.896.480 I slot print_timing: id 3 | task 1541 | n_gen = 358, tg = 4.39 t/s, tg_3s = 4.76 t/s 12.38.050.123 I slot print_timing: id 1 | task 1516 | n_gen = 397, tg = 4.33 t/s, tg_3s = 4.76 t/s 12.38.050.280 I slot print_timing: id 2 | task 1628 | n_gen = 287, tg = 4.47 t/s, tg_3s = 4.76 t/s 12.38.050.429 I slot print_timing: id 3 | task 1541 | n_gen = 373, tg = 4.41 t/s, tg_3s = 4.76 t/s 12.39.521.675 I slot print_timing: id 0 | task 1852 | prompt eval time = 1750.59 ms / 98 tokens ( 17.86 ms per token, 55.98 tokens per second) 12.39.521.680 I slot print_timing: id 0 | task 1852 | eval time = 15138.19 ms / 73 tokens ( 210.25 ms per token, 4.76 tokens per second) 12.39.521.681 I slot print_timing: id 0 | task 1852 | total time = 16888.78 ms / 171 tokens 12.39.521.681 I slot print_timing: id 0 | task 1852 | graphs reused = 1517 12.39.521.682 I slot print_timing: id 0 | task 1852 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.521.725 I slot release: id 0 | task 1852 | stop processing: n_tokens = 1295, truncated = 0 12.39.721.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.885 12.39.721.450 I slot launch_slot_: id 0 | task 1928 | processing task, is_child = 0 12.41.398.294 I slot print_timing: id 1 | task 1516 | n_gen = 406, tg = 4.27 t/s, tg_3s = 2.69 t/s 12.41.398.477 I slot print_timing: id 2 | task 1628 | n_gen = 296, tg = 4.38 t/s, tg_3s = 2.69 t/s 12.41.398.681 I slot print_timing: id 3 | task 1541 | n_gen = 382, tg = 4.34 t/s, tg_3s = 2.69 t/s 12.44.519.357 I slot print_timing: id 1 | task 1516 | n_gen = 420, tg = 4.28 t/s, tg_3s = 4.49 t/s 12.44.519.500 I slot print_timing: id 2 | task 1628 | n_gen = 310, tg = 4.38 t/s, tg_3s = 4.49 t/s 12.44.519.657 I slot print_timing: id 3 | task 1541 | n_gen = 396, tg = 4.35 t/s, tg_3s = 4.49 t/s 12.47.674.089 I slot print_timing: id 1 | task 1516 | n_gen = 435, tg = 4.29 t/s, tg_3s = 4.75 t/s 12.47.674.234 I slot print_timing: id 2 | task 1628 | n_gen = 325, tg = 4.40 t/s, tg_3s = 4.75 t/s 12.47.674.386 I slot print_timing: id 3 | task 1541 | n_gen = 411, tg = 4.36 t/s, tg_3s = 4.75 t/s 12.50.829.980 I slot print_timing: id 1 | task 1516 | n_gen = 450, tg = 4.31 t/s, tg_3s = 4.75 t/s 12.50.830.123 I slot print_timing: id 2 | task 1628 | n_gen = 340, tg = 4.41 t/s, tg_3s = 4.75 t/s 12.50.830.268 I slot print_timing: id 3 | task 1541 | n_gen = 426, tg = 4.37 t/s, tg_3s = 4.75 t/s 12.53.353.375 I slot print_timing: id 3 | task 1541 | prompt eval time = 2451.65 ms / 137 tokens ( 17.90 ms per token, 55.88 tokens per second) 12.53.353.378 I slot print_timing: id 3 | task 1541 | eval time = 99711.16 ms / 438 tokens ( 228.17 ms per token, 4.38 tokens per second) 12.53.353.378 I slot print_timing: id 3 | task 1541 | total time = 102162.80 ms / 575 tokens 12.53.353.379 I slot print_timing: id 3 | task 1541 | graphs reused = 1572 12.53.353.379 I slot print_timing: id 3 | task 1541 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.353.429 I slot release: id 3 | task 1541 | stop processing: n_tokens = 1699, truncated = 0 12.53.552.886 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.675 12.53.552.924 I slot launch_slot_: id 3 | task 1987 | processing task, is_child = 0 12.55.251.071 I slot print_timing: id 1 | task 1516 | n_gen = 464, tg = 4.26 t/s, tg_3s = 3.17 t/s 12.55.251.283 I slot print_timing: id 2 | task 1628 | n_gen = 354, tg = 4.34 t/s, tg_3s = 3.17 t/s 12.58.381.674 I slot print_timing: id 1 | task 1516 | n_gen = 478, tg = 4.27 t/s, tg_3s = 4.47 t/s 12.58.381.817 I slot print_timing: id 2 | task 1628 | n_gen = 368, tg = 4.35 t/s, tg_3s = 4.47 t/s 13.01.535.292 I slot print_timing: id 1 | task 1516 | n_gen = 493, tg = 4.28 t/s, tg_3s = 4.76 t/s 13.01.535.434 I slot print_timing: id 2 | task 1628 | n_gen = 383, tg = 4.36 t/s, tg_3s = 4.76 t/s 13.03.849.027 I slot print_timing: id 2 | task 1628 | prompt eval time = 2637.88 ms / 153 tokens ( 17.24 ms per token, 58.00 tokens per second) 13.03.849.030 I slot print_timing: id 2 | task 1628 | eval time = 89851.52 ms / 394 tokens ( 228.63 ms per token, 4.37 tokens per second) 13.03.849.031 I slot print_timing: id 2 | task 1628 | total time = 92489.40 ms / 547 tokens 13.03.849.031 I slot print_timing: id 2 | task 1628 | graphs reused = 1610 13.03.849.031 I slot print_timing: id 2 | task 1628 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.849.078 I slot release: id 2 | task 1628 | stop processing: n_tokens = 1671, truncated = 0 13.04.134.750 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.686 13.04.134.786 I slot launch_slot_: id 2 | task 2030 | processing task, is_child = 0 13.05.928.515 I slot print_timing: id 0 | task 1928 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 13.05.928.729 I slot print_timing: id 1 | task 1516 | n_gen = 506, tg = 4.23 t/s, tg_3s = 2.96 t/s 13.08.935.527 I slot print_timing: id 0 | task 1928 | n_gen = 113, tg = 4.13 t/s, tg_3s = 4.32 t/s 13.08.935.669 I slot print_timing: id 1 | task 1516 | n_gen = 519, tg = 4.23 t/s, tg_3s = 4.32 t/s 13.09.145.770 I slot print_timing: id 0 | task 1928 | prompt eval time = 2062.59 ms / 105 tokens ( 19.64 ms per token, 50.91 tokens per second) 13.09.145.775 I slot print_timing: id 0 | task 1928 | eval time = 27361.73 ms / 114 tokens ( 242.14 ms per token, 4.13 tokens per second) 13.09.145.776 I slot print_timing: id 0 | task 1928 | total time = 29424.31 ms / 219 tokens 13.09.145.776 I slot print_timing: id 0 | task 1928 | graphs reused = 1622 13.09.145.777 I slot print_timing: id 0 | task 1928 | graph reallocs = 0 / 0 (same size) / (changed size) 13.09.145.823 I slot release: id 0 | task 1928 | stop processing: n_tokens = 1343, truncated = 0 13.09.345.685 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.853 13.09.345.723 I slot launch_slot_: id 0 | task 2047 | processing task, is_child = 0 13.12.145.357 I slot print_timing: id 1 | task 1516 | n_gen = 528, tg = 4.20 t/s, tg_3s = 2.80 t/s 13.15.298.546 I slot print_timing: id 1 | task 1516 | n_gen = 543, tg = 4.21 t/s, tg_3s = 4.76 t/s 13.18.450.193 I slot print_timing: id 1 | task 1516 | n_gen = 558, tg = 4.22 t/s, tg_3s = 4.76 t/s 13.19.710.569 I slot print_timing: id 3 | task 1987 | n_gen = 100, tg = 4.11 t/s, tg_3s = 4.16 t/s 13.21.601.905 I slot print_timing: id 1 | task 1516 | n_gen = 573, tg = 4.24 t/s, tg_3s = 4.76 t/s 13.22.863.338 I slot print_timing: id 3 | task 1987 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.76 t/s 13.24.750.848 I slot print_timing: id 1 | task 1516 | n_gen = 588, tg = 4.25 t/s, tg_3s = 4.76 t/s 13.26.012.665 I slot print_timing: id 3 | task 1987 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.76 t/s 13.27.904.300 I slot print_timing: id 1 | task 1516 | n_gen = 603, tg = 4.26 t/s, tg_3s = 4.76 t/s 13.28.534.695 I slot print_timing: id 2 | task 2030 | n_gen = 100, tg = 4.47 t/s, tg_3s = 4.52 t/s 13.29.165.376 I slot print_timing: id 3 | task 1987 | n_gen = 145, tg = 4.30 t/s, tg_3s = 4.76 t/s 13.31.057.559 I slot print_timing: id 1 | task 1516 | n_gen = 618, tg = 4.27 t/s, tg_3s = 4.76 t/s 13.31.688.336 I slot print_timing: id 2 | task 2030 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.76 t/s 13.31.898.468 I slot print_timing: id 0 | task 2047 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 13.32.319.602 I slot print_timing: id 3 | task 1987 | n_gen = 160, tg = 4.34 t/s, tg_3s = 4.76 t/s 13.34.211.599 I slot print_timing: id 1 | task 1516 | n_gen = 633, tg = 4.28 t/s, tg_3s = 4.76 t/s 13.34.842.338 I slot print_timing: id 2 | task 2030 | n_gen = 130, tg = 4.54 t/s, tg_3s = 4.76 t/s 13.35.052.421 I slot print_timing: id 0 | task 2047 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 13.35.473.429 I slot print_timing: id 3 | task 1987 | n_gen = 175, tg = 4.37 t/s, tg_3s = 4.76 t/s 13.37.155.391 I slot print_timing: id 1 | task 1516 | prompt eval time = 2419.58 ms / 131 tokens ( 18.47 ms per token, 54.14 tokens per second) 13.37.155.396 I slot print_timing: id 1 | task 1516 | eval time = 150575.91 ms / 647 tokens ( 233.09 ms per token, 4.29 tokens per second) 13.37.155.396 I slot print_timing: id 1 | task 1516 | total time = 152995.49 ms / 778 tokens 13.37.155.397 I slot print_timing: id 1 | task 1516 | graphs reused = 1745 13.37.155.397 I slot print_timing: id 1 | task 1516 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.155.443 I slot release: id 1 | task 1516 | stop processing: n_tokens = 1902, truncated = 0 13.37.441.026 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.603 13.37.441.057 I slot launch_slot_: id 1 | task 2175 | processing task, is_child = 0 13.39.290.920 I slot print_timing: id 0 | task 2047 | n_gen = 127, tg = 4.47 t/s, tg_3s = 2.83 t/s 13.39.291.075 I slot print_timing: id 2 | task 2030 | n_gen = 143, tg = 4.32 t/s, tg_3s = 2.92 t/s 13.39.291.280 I slot print_timing: id 3 | task 1987 | n_gen = 185, tg = 4.22 t/s, tg_3s = 2.62 t/s 13.42.361.550 I slot print_timing: id 0 | task 2047 | n_gen = 140, tg = 4.45 t/s, tg_3s = 4.23 t/s 13.42.361.844 I slot print_timing: id 2 | task 2030 | n_gen = 156, tg = 4.31 t/s, tg_3s = 4.23 t/s 13.42.361.998 I slot print_timing: id 3 | task 1987 | n_gen = 198, tg = 4.22 t/s, tg_3s = 4.23 t/s 13.45.511.900 I slot print_timing: id 0 | task 2047 | n_gen = 155, tg = 4.47 t/s, tg_3s = 4.76 t/s 13.45.512.165 I slot print_timing: id 2 | task 2030 | n_gen = 171, tg = 4.35 t/s, tg_3s = 4.76 t/s 13.45.512.313 I slot print_timing: id 3 | task 1987 | n_gen = 213, tg = 4.25 t/s, tg_3s = 4.76 t/s 13.48.242.972 I slot print_timing: id 2 | task 2030 | prompt eval time = 2276.81 ms / 122 tokens ( 18.66 ms per token, 53.58 tokens per second) 13.48.242.975 I slot print_timing: id 2 | task 2030 | eval time = 41831.37 ms / 184 tokens ( 228.59 ms per token, 4.37 tokens per second) 13.48.242.975 I slot print_timing: id 2 | task 2030 | total time = 44108.18 ms / 306 tokens 13.48.242.976 I slot print_timing: id 2 | task 2030 | graphs reused = 1784 13.48.242.976 I slot print_timing: id 2 | task 2030 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.243.020 I slot release: id 2 | task 2030 | stop processing: n_tokens = 1430, truncated = 0 13.48.527.617 I slot print_timing: id 0 | task 2047 | n_gen = 169, tg = 4.49 t/s, tg_3s = 4.64 t/s 13.48.527.962 I slot print_timing: id 3 | task 1987 | n_gen = 227, tg = 4.27 t/s, tg_3s = 4.64 t/s 13.48.527.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.801 13.48.528.004 I slot launch_slot_: id 2 | task 2219 | processing task, is_child = 0 13.51.583.618 I slot print_timing: id 0 | task 2047 | n_gen = 173, tg = 4.25 t/s, tg_3s = 1.31 t/s 13.51.584.018 I slot print_timing: id 3 | task 1987 | prompt eval time = 2093.61 ms / 113 tokens ( 18.53 ms per token, 53.97 tokens per second) 13.51.584.021 I slot print_timing: id 3 | task 1987 | eval time = 55937.48 ms / 231 tokens ( 243.21 ms per token, 4.11 tokens per second) 13.51.584.022 I slot print_timing: id 3 | task 1987 | total time = 58031.09 ms / 344 tokens 13.51.584.022 I slot print_timing: id 3 | task 1987 | graphs reused = 1785 13.51.584.023 I slot print_timing: id 3 | task 1987 | graph reallocs = 0 / 0 (same size) / (changed size) 13.51.584.070 I slot release: id 3 | task 1987 | stop processing: n_tokens = 1468, truncated = 0 13.51.783.085 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.781 13.51.783.119 I slot launch_slot_: id 3 | task 2225 | processing task, is_child = 0 13.54.743.472 I slot print_timing: id 0 | task 2047 | n_gen = 180, tg = 4.10 t/s, tg_3s = 2.22 t/s 13.57.892.576 I slot print_timing: id 0 | task 2047 | n_gen = 195, tg = 4.15 t/s, tg_3s = 4.76 t/s 14.01.041.391 I slot print_timing: id 0 | task 2047 | n_gen = 210, tg = 4.18 t/s, tg_3s = 4.76 t/s 14.04.191.051 I slot print_timing: id 0 | task 2047 | n_gen = 225, tg = 4.22 t/s, tg_3s = 4.76 t/s 14.04.611.155 I slot print_timing: id 1 | task 2175 | n_gen = 100, tg = 4.00 t/s, tg_3s = 4.04 t/s 14.04.821.081 I slot print_timing: id 0 | task 2047 | prompt eval time = 1746.79 ms / 96 tokens ( 18.20 ms per token, 54.96 tokens per second) 14.04.821.084 I slot print_timing: id 0 | task 2047 | eval time = 53728.56 ms / 228 tokens ( 236.69 ms per token, 4.22 tokens per second) 14.04.821.084 I slot print_timing: id 0 | task 2047 | total time = 55475.35 ms / 324 tokens 14.04.821.085 I slot print_timing: id 0 | task 2047 | graphs reused = 1836 14.04.821.085 I slot print_timing: id 0 | task 2047 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.821.131 I slot release: id 0 | task 2047 | stop processing: n_tokens = 1448, truncated = 0 14.05.020.297 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.791 14.05.020.341 I slot launch_slot_: id 0 | task 2281 | processing task, is_child = 0 14.07.727.045 I slot print_timing: id 1 | task 2175 | n_gen = 107, tg = 3.80 t/s, tg_3s = 2.25 t/s 14.10.876.768 I slot print_timing: id 1 | task 2175 | n_gen = 122, tg = 3.90 t/s, tg_3s = 4.76 t/s 14.14.026.634 I slot print_timing: id 1 | task 2175 | n_gen = 137, tg = 3.98 t/s, tg_3s = 4.76 t/s 14.15.286.569 I slot print_timing: id 2 | task 2219 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.15 t/s 14.16.336.209 I slot print_timing: id 3 | task 2225 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.46 t/s 14.17.175.013 I slot print_timing: id 1 | task 2175 | n_gen = 152, tg = 4.04 t/s, tg_3s = 4.76 t/s 14.18.435.405 I slot print_timing: id 2 | task 2219 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.76 t/s 14.19.485.246 I slot print_timing: id 3 | task 2225 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 14.20.325.299 I slot print_timing: id 1 | task 2175 | n_gen = 167, tg = 4.10 t/s, tg_3s = 4.76 t/s 14.21.585.656 I slot print_timing: id 2 | task 2219 | n_gen = 130, tg = 4.24 t/s, tg_3s = 4.76 t/s 14.22.635.915 I slot print_timing: id 3 | task 2225 | n_gen = 130, tg = 4.49 t/s, tg_3s = 4.76 t/s 14.23.475.825 I slot print_timing: id 1 | task 2175 | n_gen = 182, tg = 4.15 t/s, tg_3s = 4.76 t/s 14.24.736.198 I slot print_timing: id 2 | task 2219 | n_gen = 145, tg = 4.29 t/s, tg_3s = 4.76 t/s 14.25.786.359 I slot print_timing: id 3 | task 2225 | n_gen = 145, tg = 4.52 t/s, tg_3s = 4.76 t/s 14.26.625.916 I slot print_timing: id 1 | task 2175 | n_gen = 197, tg = 4.19 t/s, tg_3s = 4.76 t/s 14.27.886.485 I slot print_timing: id 0 | task 2281 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 14.27.886.769 I slot print_timing: id 2 | task 2219 | n_gen = 160, tg = 4.33 t/s, tg_3s = 4.76 t/s 14.28.937.608 I slot print_timing: id 3 | task 2225 | n_gen = 160, tg = 4.54 t/s, tg_3s = 4.76 t/s 14.29.777.807 I slot print_timing: id 1 | task 2175 | n_gen = 212, tg = 4.23 t/s, tg_3s = 4.76 t/s 14.31.038.331 I slot print_timing: id 0 | task 2281 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 14.31.038.618 I slot print_timing: id 2 | task 2219 | n_gen = 175, tg = 4.36 t/s, tg_3s = 4.76 t/s 14.32.089.140 I slot print_timing: id 3 | task 2225 | n_gen = 175, tg = 4.56 t/s, tg_3s = 4.76 t/s 14.32.929.459 I slot print_timing: id 1 | task 2175 | n_gen = 227, tg = 4.26 t/s, tg_3s = 4.76 t/s 14.34.190.106 I slot print_timing: id 0 | task 2281 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 14.34.190.373 I slot print_timing: id 2 | task 2219 | n_gen = 190, tg = 4.39 t/s, tg_3s = 4.76 t/s 14.35.241.228 I slot print_timing: id 3 | task 2225 | n_gen = 190, tg = 4.57 t/s, tg_3s = 4.76 t/s 14.36.081.374 I slot print_timing: id 1 | task 2175 | n_gen = 242, tg = 4.29 t/s, tg_3s = 4.76 t/s 14.37.342.429 I slot print_timing: id 0 | task 2281 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 14.37.342.720 I slot print_timing: id 2 | task 2219 | n_gen = 205, tg = 4.42 t/s, tg_3s = 4.76 t/s 14.38.393.339 I slot print_timing: id 3 | task 2225 | n_gen = 205, tg = 4.59 t/s, tg_3s = 4.76 t/s 14.39.233.399 I slot print_timing: id 1 | task 2175 | n_gen = 257, tg = 4.31 t/s, tg_3s = 4.76 t/s 14.40.494.235 I slot print_timing: id 0 | task 2281 | n_gen = 160, tg = 4.76 t/s, tg_3s = 4.76 t/s 14.40.494.534 I slot print_timing: id 2 | task 2219 | n_gen = 220, tg = 4.44 t/s, tg_3s = 4.76 t/s 14.41.545.722 I slot print_timing: id 3 | task 2225 | n_gen = 220, tg = 4.60 t/s, tg_3s = 4.76 t/s 14.42.386.578 I slot print_timing: id 1 | task 2175 | n_gen = 272, tg = 4.33 t/s, tg_3s = 4.76 t/s 14.43.647.489 I slot print_timing: id 0 | task 2281 | n_gen = 175, tg = 4.76 t/s, tg_3s = 4.76 t/s 14.43.647.764 I slot print_timing: id 2 | task 2219 | n_gen = 235, tg = 4.46 t/s, tg_3s = 4.76 t/s 14.44.699.005 I slot print_timing: id 3 | task 2225 | n_gen = 235, tg = 4.61 t/s, tg_3s = 4.76 t/s 14.45.539.715 I slot print_timing: id 1 | task 2175 | n_gen = 287, tg = 4.35 t/s, tg_3s = 4.76 t/s 14.46.590.481 I slot print_timing: id 1 | task 2175 | prompt eval time = 2398.06 ms / 113 tokens ( 21.22 ms per token, 47.12 tokens per second) 14.46.590.486 I slot print_timing: id 1 | task 2175 | eval time = 66751.35 ms / 292 tokens ( 229.39 ms per token, 4.36 tokens per second) 14.46.590.487 I slot print_timing: id 1 | task 2175 | total time = 69149.42 ms / 405 tokens 14.46.590.488 I slot print_timing: id 1 | task 2175 | graphs reused = 2024 14.46.590.488 I slot print_timing: id 1 | task 2175 | graph reallocs = 0 / 0 (same size) / (changed size) 14.46.590.532 I slot release: id 1 | task 2175 | stop processing: n_tokens = 1529, truncated = 0 14.46.876.165 I slot print_timing: id 0 | task 2281 | n_gen = 190, tg = 4.75 t/s, tg_3s = 4.65 t/s 14.46.876.314 I slot print_timing: id 2 | task 2219 | n_gen = 250, tg = 4.47 t/s, tg_3s = 4.65 t/s 14.46.876.467 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.750 14.46.876.498 I slot launch_slot_: id 1 | task 2473 | processing task, is_child = 0 14.48.741.528 I slot print_timing: id 3 | task 2225 | n_gen = 246, tg = 4.47 t/s, tg_3s = 2.72 t/s 14.49.922.279 I slot print_timing: id 0 | task 2281 | n_gen = 195, tg = 4.53 t/s, tg_3s = 1.64 t/s 14.49.922.547 I slot print_timing: id 2 | task 2219 | n_gen = 255, tg = 4.32 t/s, tg_3s = 1.64 t/s 14.51.816.841 I slot print_timing: id 3 | task 2225 | n_gen = 259, tg = 4.45 t/s, tg_3s = 4.23 t/s 14.53.077.452 I slot print_timing: id 0 | task 2281 | n_gen = 210, tg = 4.55 t/s, tg_3s = 4.75 t/s 14.53.077.742 I slot print_timing: id 2 | task 2219 | n_gen = 270, tg = 4.34 t/s, tg_3s = 4.75 t/s 14.54.968.720 I slot print_timing: id 3 | task 2225 | n_gen = 274, tg = 4.47 t/s, tg_3s = 4.76 t/s 14.56.229.108 I slot print_timing: id 0 | task 2281 | prompt eval time = 2074.54 ms / 117 tokens ( 17.73 ms per token, 56.40 tokens per second) 14.56.229.111 I slot print_timing: id 0 | task 2281 | eval time = 49134.22 ms / 225 tokens ( 219.35 ms per token, 4.56 tokens per second) 14.56.229.111 I slot print_timing: id 0 | task 2281 | total time = 51208.76 ms / 342 tokens 14.56.229.112 I slot print_timing: id 0 | task 2281 | graphs reused = 2055 14.56.229.112 I slot print_timing: id 0 | task 2281 | graph reallocs = 0 / 0 (same size) / (changed size) 14.56.229.154 I slot release: id 0 | task 2281 | stop processing: n_tokens = 1466, truncated = 0 14.56.229.427 I slot print_timing: id 2 | task 2219 | n_gen = 285, tg = 4.36 t/s, tg_3s = 4.76 t/s 14.56.428.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.782 14.56.428.635 I slot launch_slot_: id 0 | task 2510 | processing task, is_child = 0 14.58.468.176 I slot print_timing: id 3 | task 2225 | n_gen = 282, tg = 4.35 t/s, tg_3s = 2.29 t/s 14.59.277.153 I slot print_timing: id 2 | task 2219 | n_gen = 290, tg = 4.24 t/s, tg_3s = 1.64 t/s 14.59.697.412 I slot print_timing: id 3 | task 2225 | prompt eval time = 2118.54 ms / 131 tokens ( 16.17 ms per token, 61.84 tokens per second) 14.59.697.417 I slot print_timing: id 3 | task 2225 | eval time = 65795.75 ms / 287 tokens ( 230.06 ms per token, 4.35 tokens per second) 14.59.697.417 I slot print_timing: id 3 | task 2225 | total time = 67914.29 ms / 418 tokens 14.59.697.418 I slot print_timing: id 3 | task 2225 | graphs reused = 2059 14.59.697.418 I slot print_timing: id 3 | task 2225 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.697.469 I slot release: id 3 | task 2225 | stop processing: n_tokens = 1542, truncated = 0 14.59.896.958 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.743 14.59.896.989 I slot launch_slot_: id 3 | task 2518 | processing task, is_child = 0 15.02.300.013 I slot print_timing: id 2 | task 2219 | n_gen = 298, tg = 4.17 t/s, tg_3s = 2.65 t/s 15.05.450.019 I slot print_timing: id 2 | task 2219 | n_gen = 313, tg = 4.20 t/s, tg_3s = 4.76 t/s 15.08.600.118 I slot print_timing: id 2 | task 2219 | n_gen = 328, tg = 4.22 t/s, tg_3s = 4.76 t/s 15.11.750.098 I slot print_timing: id 2 | task 2219 | n_gen = 343, tg = 4.24 t/s, tg_3s = 4.76 t/s 15.13.429.587 I slot print_timing: id 1 | task 2473 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 15.14.900.601 I slot print_timing: id 2 | task 2219 | n_gen = 358, tg = 4.26 t/s, tg_3s = 4.76 t/s 15.16.580.342 I slot print_timing: id 1 | task 2473 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.76 t/s 15.18.050.804 I slot print_timing: id 2 | task 2219 | n_gen = 373, tg = 4.28 t/s, tg_3s = 4.76 t/s 15.19.731.408 I slot print_timing: id 1 | task 2473 | n_gen = 130, tg = 4.24 t/s, tg_3s = 4.76 t/s 15.20.992.296 I slot print_timing: id 0 | task 2510 | n_gen = 100, tg = 4.47 t/s, tg_3s = 4.52 t/s 15.21.202.647 I slot print_timing: id 2 | task 2219 | n_gen = 388, tg = 4.30 t/s, tg_3s = 4.76 t/s 15.22.463.246 I slot print_timing: id 3 | task 2518 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 15.22.883.058 I slot print_timing: id 1 | task 2473 | n_gen = 145, tg = 4.29 t/s, tg_3s = 4.76 t/s 15.24.143.458 I slot print_timing: id 0 | task 2510 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.76 t/s 15.24.354.005 I slot print_timing: id 2 | task 2219 | n_gen = 403, tg = 4.31 t/s, tg_3s = 4.76 t/s 15.25.615.273 I slot print_timing: id 3 | task 2518 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 15.26.034.990 I slot print_timing: id 1 | task 2473 | n_gen = 160, tg = 4.33 t/s, tg_3s = 4.76 t/s 15.27.295.633 I slot print_timing: id 0 | task 2510 | n_gen = 130, tg = 4.54 t/s, tg_3s = 4.76 t/s 15.27.506.094 I slot print_timing: id 2 | task 2219 | n_gen = 418, tg = 4.33 t/s, tg_3s = 4.76 t/s 15.28.766.572 I slot print_timing: id 3 | task 2518 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 15.29.186.869 I slot print_timing: id 1 | task 2473 | n_gen = 175, tg = 4.36 t/s, tg_3s = 4.76 t/s 15.30.447.425 I slot print_timing: id 0 | task 2510 | n_gen = 145, tg = 4.56 t/s, tg_3s = 4.76 t/s 15.30.657.934 I slot print_timing: id 2 | task 2219 | prompt eval time = 2633.52 ms / 149 tokens ( 17.67 ms per token, 56.58 tokens per second) 15.30.657.939 I slot print_timing: id 2 | task 2219 | eval time = 99496.40 ms / 433 tokens ( 230.32 ms per token, 4.34 tokens per second) 15.30.657.940 I slot print_timing: id 2 | task 2219 | total time = 102129.92 ms / 582 tokens 15.30.657.940 I slot print_timing: id 2 | task 2219 | graphs reused = 2196 15.30.657.941 I slot print_timing: id 2 | task 2219 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.657.995 I slot release: id 2 | task 2219 | stop processing: n_tokens = 1706, truncated = 0 15.30.943.893 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.672 15.30.943.929 I slot launch_slot_: id 2 | task 2660 | processing task, is_child = 0 15.32.720.049 I slot print_timing: id 1 | task 2473 | n_gen = 184, tg = 4.21 t/s, tg_3s = 2.55 t/s 15.32.720.263 I slot print_timing: id 3 | task 2518 | n_gen = 141, tg = 4.51 t/s, tg_3s = 2.78 t/s 15.33.625.940 I slot print_timing: id 0 | task 2510 | n_gen = 151, tg = 4.31 t/s, tg_3s = 1.89 t/s 15.35.726.446 I slot print_timing: id 1 | task 2473 | n_gen = 197, tg = 4.22 t/s, tg_3s = 4.32 t/s 15.35.726.753 I slot print_timing: id 3 | task 2518 | n_gen = 154, tg = 4.49 t/s, tg_3s = 4.32 t/s 15.36.775.247 I slot print_timing: id 0 | task 2510 | n_gen = 166, tg = 4.35 t/s, tg_3s = 4.76 t/s 15.38.876.040 I slot print_timing: id 1 | task 2473 | n_gen = 212, tg = 4.26 t/s, tg_3s = 4.76 t/s 15.38.876.333 I slot print_timing: id 3 | task 2518 | n_gen = 169, tg = 4.52 t/s, tg_3s = 4.76 t/s 15.39.925.939 I slot print_timing: id 0 | task 2510 | n_gen = 181, tg = 4.38 t/s, tg_3s = 4.76 t/s 15.42.027.265 I slot print_timing: id 1 | task 2473 | n_gen = 227, tg = 4.29 t/s, tg_3s = 4.76 t/s 15.42.027.574 I slot print_timing: id 3 | task 2518 | n_gen = 184, tg = 4.53 t/s, tg_3s = 4.76 t/s 15.43.077.247 I slot print_timing: id 0 | task 2510 | n_gen = 196, tg = 4.41 t/s, tg_3s = 4.76 t/s 15.45.178.660 I slot print_timing: id 1 | task 2473 | n_gen = 242, tg = 4.31 t/s, tg_3s = 4.76 t/s 15.45.178.956 I slot print_timing: id 3 | task 2518 | n_gen = 199, tg = 4.55 t/s, tg_3s = 4.76 t/s 15.46.228.947 I slot print_timing: id 0 | task 2510 | n_gen = 211, tg = 4.43 t/s, tg_3s = 4.76 t/s 15.48.329.613 I slot print_timing: id 1 | task 2473 | n_gen = 257, tg = 4.34 t/s, tg_3s = 4.76 t/s 15.48.329.885 I slot print_timing: id 3 | task 2518 | n_gen = 214, tg = 4.56 t/s, tg_3s = 4.76 t/s 15.48.539.900 I slot print_timing: id 3 | task 2518 | prompt eval time = 1770.87 ms / 96 tokens ( 18.45 ms per token, 54.21 tokens per second) 15.48.539.903 I slot print_timing: id 3 | task 2518 | eval time = 46872.03 ms / 215 tokens ( 219.03 ms per token, 4.57 tokens per second) 15.48.539.904 I slot print_timing: id 3 | task 2518 | total time = 48642.91 ms / 311 tokens 15.48.539.904 I slot print_timing: id 3 | task 2518 | graphs reused = 2268 15.48.539.905 I slot print_timing: id 3 | task 2518 | graph reallocs = 0 / 0 (same size) / (changed size) 15.48.539.951 I slot release: id 3 | task 2518 | stop processing: n_tokens = 1435, truncated = 0 15.48.738.683 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.799 15.48.738.716 I slot launch_slot_: id 3 | task 2737 | processing task, is_child = 0 15.50.116.553 I slot print_timing: id 0 | task 2510 | n_gen = 224, tg = 4.35 t/s, tg_3s = 3.34 t/s 15.51.356.516 I slot print_timing: id 1 | task 2473 | n_gen = 265, tg = 4.25 t/s, tg_3s = 2.64 t/s 15.53.247.158 I slot print_timing: id 0 | task 2510 | n_gen = 238, tg = 4.36 t/s, tg_3s = 4.47 t/s 15.53.247.438 I slot print_timing: id 2 | task 2660 | prompt eval time = 2259.68 ms / 104 tokens ( 21.73 ms per token, 46.02 tokens per second) 15.53.247.439 I slot print_timing: id 2 | task 2660 | eval time = 20043.83 ms / 90 tokens ( 225.21 ms per token, 4.44 tokens per second) 15.53.247.440 I slot print_timing: id 2 | task 2660 | total time = 22303.50 ms / 194 tokens 15.53.247.440 I slot print_timing: id 2 | task 2660 | graphs reused = 2280 15.53.247.441 I slot print_timing: id 2 | task 2660 | graph reallocs = 0 / 0 (same size) / (changed size) 15.53.247.485 I slot release: id 2 | task 2660 | stop processing: n_tokens = 1318, truncated = 0 15.53.533.071 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.869 15.53.533.104 I slot launch_slot_: id 2 | task 2754 | processing task, is_child = 0 15.55.310.018 I slot print_timing: id 1 | task 2473 | n_gen = 276, tg = 4.17 t/s, tg_3s = 2.78 t/s 15.56.426.282 I slot print_timing: id 0 | task 2510 | n_gen = 244, tg = 4.22 t/s, tg_3s = 1.89 t/s 15.58.318.459 I slot print_timing: id 1 | task 2473 | n_gen = 289, tg = 4.17 t/s, tg_3s = 4.32 t/s 15.59.578.580 I slot print_timing: id 0 | task 2510 | n_gen = 259, tg = 4.25 t/s, tg_3s = 4.76 t/s 16.01.469.221 I slot print_timing: id 1 | task 2473 | n_gen = 304, tg = 4.20 t/s, tg_3s = 4.76 t/s 16.02.729.911 I slot print_timing: id 0 | task 2510 | n_gen = 274, tg = 4.27 t/s, tg_3s = 4.76 t/s 16.04.620.522 I slot print_timing: id 1 | task 2473 | n_gen = 319, tg = 4.22 t/s, tg_3s = 4.76 t/s 16.05.880.917 I slot print_timing: id 0 | task 2510 | n_gen = 289, tg = 4.30 t/s, tg_3s = 4.76 t/s 16.07.772.083 I slot print_timing: id 1 | task 2473 | n_gen = 334, tg = 4.24 t/s, tg_3s = 4.76 t/s 16.09.032.303 I slot print_timing: id 0 | task 2510 | n_gen = 304, tg = 4.32 t/s, tg_3s = 4.76 t/s 16.10.293.515 I slot print_timing: id 2 | task 2754 | prompt eval time = 2260.90 ms / 102 tokens ( 22.17 ms per token, 45.11 tokens per second) 16.10.293.521 I slot print_timing: id 2 | task 2754 | eval time = 14499.50 ms / 70 tokens ( 210.14 ms per token, 4.76 tokens per second) 16.10.293.521 I slot print_timing: id 2 | task 2754 | total time = 16760.40 ms / 172 tokens 16.10.293.522 I slot print_timing: id 2 | task 2754 | graphs reused = 2347 16.10.293.522 I slot print_timing: id 2 | task 2754 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.293.565 I slot release: id 2 | task 2754 | stop processing: n_tokens = 1296, truncated = 0 16.10.578.746 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.884 16.10.578.785 I slot launch_slot_: id 2 | task 2827 | processing task, is_child = 0 16.12.359.925 I slot print_timing: id 0 | task 2510 | n_gen = 312, tg = 4.23 t/s, tg_3s = 2.40 t/s 16.12.360.092 I slot print_timing: id 1 | task 2473 | n_gen = 348, tg = 4.18 t/s, tg_3s = 3.05 t/s 16.13.685.968 I slot print_timing: id 3 | task 2737 | prompt eval time = 1775.40 ms / 98 tokens ( 18.12 ms per token, 55.20 tokens per second) 16.13.685.974 I slot print_timing: id 3 | task 2737 | eval time = 23171.85 ms / 93 tokens ( 251.87 ms per token, 3.97 tokens per second) 16.13.685.974 I slot print_timing: id 3 | task 2737 | total time = 24947.24 ms / 191 tokens 16.13.685.975 I slot print_timing: id 3 | task 2737 | graphs reused = 2350 16.13.685.975 I slot print_timing: id 3 | task 2737 | graph reallocs = 0 / 0 (same size) / (changed size) 16.13.686.018 I slot release: id 3 | task 2737 | stop processing: n_tokens = 1315, truncated = 0 16.13.885.024 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.871 16.13.885.056 I slot launch_slot_: id 3 | task 2835 | processing task, is_child = 0 16.15.592.013 I slot print_timing: id 0 | task 2510 | n_gen = 319, tg = 4.14 t/s, tg_3s = 2.17 t/s 16.15.592.164 I slot print_timing: id 1 | task 2473 | n_gen = 355, tg = 4.10 t/s, tg_3s = 2.17 t/s 16.18.722.718 I slot print_timing: id 0 | task 2510 | n_gen = 333, tg = 4.16 t/s, tg_3s = 4.47 t/s 16.18.722.858 I slot print_timing: id 1 | task 2473 | n_gen = 369, tg = 4.11 t/s, tg_3s = 4.47 t/s 16.21.875.593 I slot print_timing: id 0 | task 2510 | n_gen = 348, tg = 4.18 t/s, tg_3s = 4.76 t/s 16.21.875.741 I slot print_timing: id 1 | task 2473 | n_gen = 384, tg = 4.14 t/s, tg_3s = 4.76 t/s 16.24.187.718 I slot print_timing: id 0 | task 2510 | prompt eval time = 2425.71 ms / 137 tokens ( 17.71 ms per token, 56.48 tokens per second) 16.24.187.723 I slot print_timing: id 0 | task 2510 | eval time = 85333.37 ms / 359 tokens ( 238.36 ms per token, 4.20 tokens per second) 16.24.187.723 I slot print_timing: id 0 | task 2510 | total time = 87759.08 ms / 496 tokens 16.24.187.724 I slot print_timing: id 0 | task 2510 | graphs reused = 2388 16.24.187.724 I slot print_timing: id 0 | task 2510 | graph reallocs = 0 / 0 (same size) / (changed size) 16.24.187.769 I slot release: id 0 | task 2510 | stop processing: n_tokens = 1620, truncated = 0 16.24.387.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.707 16.24.387.710 I slot launch_slot_: id 0 | task 2878 | processing task, is_child = 0 16.26.082.797 I slot print_timing: id 1 | task 2473 | n_gen = 397, tg = 4.09 t/s, tg_3s = 3.09 t/s 16.29.202.541 I slot print_timing: id 1 | task 2473 | n_gen = 411, tg = 4.10 t/s, tg_3s = 4.49 t/s 16.32.353.084 I slot print_timing: id 1 | task 2473 | n_gen = 426, tg = 4.12 t/s, tg_3s = 4.76 t/s 16.35.503.518 I slot print_timing: id 1 | task 2473 | n_gen = 441, tg = 4.14 t/s, tg_3s = 4.76 t/s 16.36.973.712 I slot print_timing: id 2 | task 2827 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 16.38.444.173 I slot print_timing: id 3 | task 2835 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 16.38.653.957 I slot print_timing: id 1 | task 2473 | n_gen = 456, tg = 4.16 t/s, tg_3s = 4.76 t/s 16.39.704.327 I slot print_timing: id 2 | task 2827 | prompt eval time = 2264.10 ms / 108 tokens ( 20.96 ms per token, 47.70 tokens per second) 16.39.704.331 I slot print_timing: id 2 | task 2827 | eval time = 26861.43 ms / 113 tokens ( 239.83 ms per token, 4.17 tokens per second) 16.39.704.331 I slot print_timing: id 2 | task 2827 | total time = 29125.54 ms / 221 tokens 16.39.704.332 I slot print_timing: id 2 | task 2827 | graphs reused = 2451 16.39.704.332 I slot print_timing: id 2 | task 2827 | graph reallocs = 0 / 0 (same size) / (changed size) 16.39.704.379 I slot release: id 2 | task 2827 | stop processing: n_tokens = 1345, truncated = 0 16.39.989.942 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.852 16.39.989.979 I slot launch_slot_: id 2 | task 2945 | processing task, is_child = 0 16.41.772.743 I slot print_timing: id 1 | task 2473 | n_gen = 463, tg = 4.11 t/s, tg_3s = 2.24 t/s 16.41.772.948 I slot print_timing: id 3 | task 2835 | n_gen = 108, tg = 4.15 t/s, tg_3s = 2.40 t/s 16.44.779.400 I slot print_timing: id 1 | task 2473 | n_gen = 476, tg = 4.11 t/s, tg_3s = 4.32 t/s 16.44.779.705 I slot print_timing: id 3 | task 2835 | n_gen = 121, tg = 4.17 t/s, tg_3s = 4.32 t/s 16.47.930.274 I slot print_timing: id 1 | task 2473 | n_gen = 491, tg = 4.13 t/s, tg_3s = 4.76 t/s 16.47.930.556 I slot print_timing: id 3 | task 2835 | n_gen = 136, tg = 4.23 t/s, tg_3s = 4.76 t/s 16.48.980.620 I slot print_timing: id 1 | task 2473 | prompt eval time = 2412.93 ms / 127 tokens ( 19.00 ms per token, 52.63 tokens per second) 16.48.980.626 I slot print_timing: id 1 | task 2473 | eval time = 119691.18 ms / 496 tokens ( 241.80 ms per token, 4.14 tokens per second) 16.48.980.627 I slot print_timing: id 1 | task 2473 | total time = 122104.11 ms / 623 tokens 16.48.980.627 I slot print_timing: id 1 | task 2473 | graphs reused = 2482 16.48.980.628 I slot print_timing: id 1 | task 2473 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.980.678 I slot release: id 1 | task 2473 | stop processing: n_tokens = 1747, truncated = 0 16.49.265.808 I slot print_timing: id 0 | task 2878 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.39 t/s 16.49.266.123 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.656 16.49.266.157 I slot launch_slot_: id 1 | task 2981 | processing task, is_child = 0 16.51.332.412 I slot print_timing: id 3 | task 2835 | n_gen = 144, tg = 4.05 t/s, tg_3s = 2.35 t/s 16.52.383.973 I slot print_timing: id 0 | task 2878 | n_gen = 107, tg = 4.09 t/s, tg_3s = 2.24 t/s 16.54.484.015 I slot print_timing: id 3 | task 2835 | n_gen = 159, tg = 4.10 t/s, tg_3s = 4.76 t/s 16.55.533.767 I slot print_timing: id 0 | task 2878 | n_gen = 122, tg = 4.16 t/s, tg_3s = 4.76 t/s 16.57.633.334 I slot print_timing: id 3 | task 2835 | n_gen = 174, tg = 4.15 t/s, tg_3s = 4.76 t/s 16.58.682.834 I slot print_timing: id 0 | task 2878 | n_gen = 137, tg = 4.22 t/s, tg_3s = 4.76 t/s 16.59.942.970 I slot print_timing: id 3 | task 2835 | prompt eval time = 2104.10 ms / 122 tokens ( 17.25 ms per token, 57.98 tokens per second) 16.59.942.976 I slot print_timing: id 3 | task 2835 | eval time = 43953.80 ms / 185 tokens ( 238.88 ms per token, 4.19 tokens per second) 16.59.942.976 I slot print_timing: id 3 | task 2835 | total time = 46057.90 ms / 307 tokens 16.59.942.977 I slot print_timing: id 3 | task 2835 | graphs reused = 2522 16.59.942.977 I slot print_timing: id 3 | task 2835 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.943.022 I slot release: id 3 | task 2835 | stop processing: n_tokens = 1431, truncated = 0 17.00.141.768 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.801 17.00.141.801 I slot launch_slot_: id 3 | task 3026 | processing task, is_child = 0 17.01.834.046 I slot print_timing: id 0 | task 2878 | n_gen = 145, tg = 4.07 t/s, tg_3s = 2.54 t/s 17.04.752.854 I slot print_timing: id 1 | task 2981 | prompt eval time = 2065.97 ms / 86 tokens ( 24.02 ms per token, 41.63 tokens per second) 17.04.752.859 I slot print_timing: id 1 | task 2981 | eval time = 13420.72 ms / 57 tokens ( 239.66 ms per token, 4.17 tokens per second) 17.04.752.860 I slot print_timing: id 1 | task 2981 | total time = 15486.69 ms / 143 tokens 17.04.752.860 I slot print_timing: id 1 | task 2981 | graphs reused = 2533 17.04.752.861 I slot print_timing: id 1 | task 2981 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.752.903 I slot release: id 1 | task 2981 | stop processing: n_tokens = 1267, truncated = 0 17.05.037.830 I slot print_timing: id 0 | task 2878 | n_gen = 159, tg = 4.10 t/s, tg_3s = 4.37 t/s 17.05.038.133 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.904 17.05.038.165 I slot launch_slot_: id 1 | task 3042 | processing task, is_child = 0 17.08.167.273 I slot print_timing: id 0 | task 2878 | n_gen = 166, tg = 3.96 t/s, tg_3s = 2.24 t/s 17.08.167.557 I slot print_timing: id 2 | task 2945 | n_gen = 100, tg = 3.82 t/s, tg_3s = 3.86 t/s 17.11.315.542 I slot print_timing: id 0 | task 2878 | n_gen = 181, tg = 4.01 t/s, tg_3s = 4.76 t/s 17.11.315.812 I slot print_timing: id 2 | task 2945 | n_gen = 115, tg = 3.92 t/s, tg_3s = 4.76 t/s 17.14.464.724 I slot print_timing: id 0 | task 2878 | n_gen = 196, tg = 4.06 t/s, tg_3s = 4.76 t/s 17.14.465.014 I slot print_timing: id 2 | task 2945 | n_gen = 130, tg = 4.01 t/s, tg_3s = 4.76 t/s 17.17.615.261 I slot print_timing: id 0 | task 2878 | n_gen = 211, tg = 4.11 t/s, tg_3s = 4.76 t/s 17.17.615.526 I slot print_timing: id 2 | task 2945 | n_gen = 145, tg = 4.07 t/s, tg_3s = 4.76 t/s 17.18.666.449 I slot print_timing: id 2 | task 2945 | prompt eval time = 2266.78 ms / 111 tokens ( 20.42 ms per token, 48.97 tokens per second) 17.18.666.452 I slot print_timing: id 2 | task 2945 | eval time = 36409.68 ms / 150 tokens ( 244.36 ms per token, 4.09 tokens per second) 17.18.666.453 I slot print_timing: id 2 | task 2945 | total time = 38676.46 ms / 261 tokens 17.18.666.453 I slot print_timing: id 2 | task 2945 | graphs reused = 2587 17.18.666.454 I slot print_timing: id 2 | task 2945 | graph reallocs = 0 / 0 (same size) / (changed size) 17.18.666.498 I slot release: id 2 | task 2945 | stop processing: n_tokens = 1385, truncated = 0 17.18.951.769 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.827 17.18.951.810 I slot launch_slot_: id 2 | task 3101 | processing task, is_child = 0 17.20.891.244 I slot print_timing: id 0 | task 2878 | n_gen = 219, tg = 4.01 t/s, tg_3s = 2.44 t/s 17.24.043.380 I slot print_timing: id 0 | task 2878 | n_gen = 234, tg = 4.05 t/s, tg_3s = 4.76 t/s 17.26.354.278 I slot print_timing: id 3 | task 3026 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.15 t/s 17.27.193.802 I slot print_timing: id 0 | task 2878 | n_gen = 249, tg = 4.08 t/s, tg_3s = 4.76 t/s 17.29.505.006 I slot print_timing: id 1 | task 3042 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.47 t/s 17.29.505.275 I slot print_timing: id 3 | task 3026 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.76 t/s 17.30.344.942 I slot print_timing: id 0 | task 2878 | n_gen = 264, tg = 4.12 t/s, tg_3s = 4.76 t/s 17.32.655.568 I slot print_timing: id 1 | task 3042 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 17.32.655.859 I slot print_timing: id 3 | task 3026 | n_gen = 130, tg = 4.24 t/s, tg_3s = 4.76 t/s 17.33.075.599 I slot print_timing: id 1 | task 3042 | prompt eval time = 2076.79 ms / 98 tokens ( 21.19 ms per token, 47.19 tokens per second) 17.33.075.601 I slot print_timing: id 1 | task 3042 | eval time = 25960.64 ms / 117 tokens ( 223.80 ms per token, 4.47 tokens per second) 17.33.075.602 I slot print_timing: id 1 | task 3042 | total time = 28037.43 ms / 215 tokens 17.33.075.602 I slot print_timing: id 1 | task 3042 | graphs reused = 2644 17.33.075.603 I slot print_timing: id 1 | task 3042 | graph reallocs = 0 / 0 (same size) / (changed size) 17.33.075.649 I slot release: id 1 | task 3042 | stop processing: n_tokens = 1339, truncated = 0 17.33.361.312 I slot print_timing: id 0 | task 2878 | n_gen = 278, tg = 4.14 t/s, tg_3s = 4.64 t/s 17.33.361.624 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.856 17.33.361.658 I slot launch_slot_: id 1 | task 3163 | processing task, is_child = 0 17.35.770.995 I slot print_timing: id 3 | task 3026 | n_gen = 135, tg = 4.00 t/s, tg_3s = 1.61 t/s 17.36.402.874 I slot print_timing: id 0 | task 2878 | n_gen = 283, tg = 4.03 t/s, tg_3s = 1.64 t/s 17.38.926.453 I slot print_timing: id 3 | task 3026 | n_gen = 150, tg = 4.06 t/s, tg_3s = 4.75 t/s 17.39.556.511 I slot print_timing: id 0 | task 2878 | n_gen = 298, tg = 4.06 t/s, tg_3s = 4.76 t/s 17.42.078.188 I slot print_timing: id 3 | task 3026 | n_gen = 165, tg = 4.12 t/s, tg_3s = 4.76 t/s 17.42.707.799 I slot print_timing: id 0 | task 2878 | n_gen = 313, tg = 4.09 t/s, tg_3s = 4.76 t/s 17.42.917.892 I slot print_timing: id 2 | task 3101 | prompt eval time = 1939.85 ms / 91 tokens ( 21.32 ms per token, 46.91 tokens per second) 17.42.917.897 I slot print_timing: id 2 | task 3101 | eval time = 22026.22 ms / 96 tokens ( 231.85 ms per token, 4.31 tokens per second) 17.42.917.897 I slot print_timing: id 2 | task 3101 | total time = 23966.07 ms / 187 tokens 17.42.917.898 I slot print_timing: id 2 | task 3101 | graphs reused = 2676 17.42.917.898 I slot print_timing: id 2 | task 3101 | graph reallocs = 0 / 0 (same size) / (changed size) 17.42.917.940 I slot release: id 2 | task 3101 | stop processing: n_tokens = 1311, truncated = 0 17.43.202.997 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.874 17.43.203.030 I slot launch_slot_: id 2 | task 3201 | processing task, is_child = 0 17.45.466.184 I slot print_timing: id 3 | task 3026 | n_gen = 172, tg = 3.96 t/s, tg_3s = 2.07 t/s 17.45.888.577 I slot print_timing: id 0 | task 2878 | n_gen = 319, tg = 4.00 t/s, tg_3s = 1.89 t/s 17.48.619.691 I slot print_timing: id 3 | task 3026 | n_gen = 187, tg = 4.01 t/s, tg_3s = 4.76 t/s 17.49.039.349 I slot print_timing: id 0 | task 2878 | n_gen = 334, tg = 4.03 t/s, tg_3s = 4.76 t/s 17.49.249.471 I slot print_timing: id 1 | task 3163 | prompt eval time = 2409.05 ms / 121 tokens ( 19.91 ms per token, 50.23 tokens per second) 17.49.249.473 I slot print_timing: id 1 | task 3163 | eval time = 13478.75 ms / 56 tokens ( 245.07 ms per token, 4.08 tokens per second) 17.49.249.474 I slot print_timing: id 1 | task 3163 | total time = 15887.81 ms / 177 tokens 17.49.249.474 I slot print_timing: id 1 | task 3163 | graphs reused = 2693 17.49.249.475 I slot print_timing: id 1 | task 3163 | graph reallocs = 0 / 0 (same size) / (changed size) 17.49.249.518 I slot release: id 1 | task 3163 | stop processing: n_tokens = 1301, truncated = 0 17.49.534.953 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.881 17.49.534.995 I slot launch_slot_: id 1 | task 3223 | processing task, is_child = 0 17.51.820.455 I slot print_timing: id 3 | task 3026 | n_gen = 194, tg = 3.89 t/s, tg_3s = 2.19 t/s 17.52.240.208 I slot print_timing: id 0 | task 2878 | n_gen = 341, tg = 3.96 t/s, tg_3s = 2.19 t/s 17.54.970.501 I slot print_timing: id 3 | task 3026 | n_gen = 209, tg = 3.94 t/s, tg_3s = 4.76 t/s 17.55.390.141 I slot print_timing: id 0 | task 2878 | n_gen = 356, tg = 3.99 t/s, tg_3s = 4.76 t/s 17.58.121.585 I slot print_timing: id 3 | task 3026 | n_gen = 224, tg = 3.99 t/s, tg_3s = 4.76 t/s 17.58.331.642 I slot print_timing: id 3 | task 3026 | prompt eval time = 2089.25 ms / 106 tokens ( 19.71 ms per token, 50.74 tokens per second) 17.58.331.647 I slot print_timing: id 3 | task 3026 | eval time = 56100.58 ms / 225 tokens ( 250.45 ms per token, 3.99 tokens per second) 17.58.331.648 I slot print_timing: id 3 | task 3026 | total time = 58189.83 ms / 331 tokens 17.58.331.648 I slot print_timing: id 3 | task 3026 | graphs reused = 2724 17.58.331.649 I slot print_timing: id 3 | task 3026 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.331.705 I slot release: id 3 | task 3026 | stop processing: n_tokens = 1455, truncated = 0 17.58.530.320 I slot print_timing: id 0 | task 2878 | n_gen = 371, tg = 4.02 t/s, tg_3s = 4.78 t/s 17.58.530.605 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.788 17.58.530.636 I slot launch_slot_: id 3 | task 3259 | processing task, is_child = 0 18.01.621.092 I slot print_timing: id 0 | task 2878 | n_gen = 376, tg = 3.94 t/s, tg_3s = 1.62 t/s 18.04.771.924 I slot print_timing: id 0 | task 2878 | n_gen = 391, tg = 3.97 t/s, tg_3s = 4.76 t/s 18.07.713.084 I slot print_timing: id 2 | task 3201 | prompt eval time = 2263.00 ms / 105 tokens ( 21.55 ms per token, 46.40 tokens per second) 18.07.713.090 I slot print_timing: id 2 | task 3201 | eval time = 22247.05 ms / 89 tokens ( 252.81 ms per token, 3.96 tokens per second) 18.07.713.090 I slot print_timing: id 2 | task 3201 | total time = 24510.05 ms / 194 tokens 18.07.713.091 I slot print_timing: id 2 | task 3201 | graphs reused = 2755 18.07.713.091 I slot print_timing: id 2 | task 3201 | graph reallocs = 0 / 0 (same size) / (changed size) 18.07.713.137 I slot release: id 2 | task 3201 | stop processing: n_tokens = 1318, truncated = 0 18.07.998.067 I slot print_timing: id 0 | task 2878 | n_gen = 406, tg = 3.99 t/s, tg_3s = 4.65 t/s 18.07.998.419 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.869 18.07.998.452 I slot launch_slot_: id 2 | task 3295 | processing task, is_child = 0 18.11.105.607 I slot print_timing: id 0 | task 2878 | n_gen = 412, tg = 3.93 t/s, tg_3s = 1.93 t/s 18.14.255.335 I slot print_timing: id 0 | task 2878 | n_gen = 427, tg = 3.95 t/s, tg_3s = 4.76 t/s 18.16.356.494 I slot print_timing: id 1 | task 3223 | n_gen = 100, tg = 4.00 t/s, tg_3s = 4.04 t/s 18.16.986.410 I slot print_timing: id 1 | task 3223 | prompt eval time = 2072.89 ms / 95 tokens ( 21.82 ms per token, 45.83 tokens per second) 18.16.986.414 I slot print_timing: id 1 | task 3223 | eval time = 25378.51 ms / 103 tokens ( 248.81 ms per token, 4.02 tokens per second) 18.16.986.414 I slot print_timing: id 1 | task 3223 | total time = 27451.40 ms / 198 tokens 18.16.986.415 I slot print_timing: id 1 | task 3223 | graphs reused = 2786 18.16.986.415 I slot print_timing: id 1 | task 3223 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.986.463 I slot release: id 1 | task 3223 | stop processing: n_tokens = 1322, truncated = 0 18.17.272.071 I slot print_timing: id 0 | task 2878 | n_gen = 441, tg = 3.97 t/s, tg_3s = 4.64 t/s 18.17.272.364 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.867 18.17.272.414 I slot launch_slot_: id 1 | task 3331 | processing task, is_child = 0 18.20.469.508 I slot print_timing: id 0 | task 2878 | n_gen = 445, tg = 3.89 t/s, tg_3s = 1.25 t/s 18.23.620.710 I slot print_timing: id 0 | task 2878 | n_gen = 460, tg = 3.92 t/s, tg_3s = 4.76 t/s 18.26.142.275 I slot print_timing: id 3 | task 3259 | n_gen = 100, tg = 3.94 t/s, tg_3s = 3.98 t/s 18.26.770.756 I slot print_timing: id 0 | task 2878 | n_gen = 475, tg = 3.94 t/s, tg_3s = 4.76 t/s 18.29.291.595 I slot print_timing: id 3 | task 3259 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.76 t/s 18.29.922.107 I slot print_timing: id 0 | task 2878 | n_gen = 490, tg = 3.96 t/s, tg_3s = 4.76 t/s 18.32.444.776 I slot print_timing: id 3 | task 3259 | n_gen = 130, tg = 4.10 t/s, tg_3s = 4.76 t/s 18.33.073.958 I slot print_timing: id 0 | task 2878 | n_gen = 505, tg = 3.98 t/s, tg_3s = 4.76 t/s 18.33.494.717 I slot print_timing: id 2 | task 3295 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.30 t/s 18.35.596.514 I slot print_timing: id 3 | task 3259 | n_gen = 145, tg = 4.16 t/s, tg_3s = 4.76 t/s 18.36.226.722 I slot print_timing: id 0 | task 2878 | n_gen = 520, tg = 4.00 t/s, tg_3s = 4.76 t/s 18.36.647.527 I slot print_timing: id 2 | task 3295 | n_gen = 115, tg = 4.32 t/s, tg_3s = 4.76 t/s 18.38.750.253 I slot print_timing: id 3 | task 3259 | n_gen = 160, tg = 4.21 t/s, tg_3s = 4.76 t/s 18.39.380.613 I slot print_timing: id 0 | task 2878 | n_gen = 535, tg = 4.02 t/s, tg_3s = 4.76 t/s 18.39.801.466 I slot print_timing: id 2 | task 3295 | n_gen = 130, tg = 4.37 t/s, tg_3s = 4.76 t/s 18.40.852.333 I slot print_timing: id 1 | task 3331 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 18.41.906.343 I slot print_timing: id 3 | task 3259 | n_gen = 175, tg = 4.25 t/s, tg_3s = 4.75 t/s 18.42.536.822 I slot print_timing: id 0 | task 2878 | n_gen = 550, tg = 4.03 t/s, tg_3s = 4.75 t/s 18.42.957.582 I slot print_timing: id 2 | task 3295 | n_gen = 145, tg = 4.40 t/s, tg_3s = 4.75 t/s 18.44.008.157 I slot print_timing: id 1 | task 3331 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.75 t/s 18.44.218.802 I slot print_timing: id 2 | task 3295 | prompt eval time = 2264.97 ms / 110 tokens ( 20.59 ms per token, 48.57 tokens per second) 18.44.218.804 I slot print_timing: id 2 | task 3295 | eval time = 33955.36 ms / 151 tokens ( 226.37 ms per token, 4.42 tokens per second) 18.44.218.805 I slot print_timing: id 2 | task 3295 | total time = 36220.34 ms / 261 tokens 18.44.218.805 I slot print_timing: id 2 | task 3295 | graphs reused = 2899 18.44.218.806 I slot print_timing: id 2 | task 3295 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.218.855 I slot release: id 2 | task 3295 | stop processing: n_tokens = 1385, truncated = 0 18.44.504.535 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.827 18.44.504.570 I slot launch_slot_: id 2 | task 3450 | processing task, is_child = 0 18.46.292.156 I slot print_timing: id 0 | task 2878 | n_gen = 560, tg = 4.00 t/s, tg_3s = 2.66 t/s 18.46.292.531 I slot print_timing: id 3 | task 3259 | n_gen = 188, tg = 4.13 t/s, tg_3s = 2.96 t/s 18.47.199.144 I slot print_timing: id 1 | task 3331 | n_gen = 121, tg = 4.42 t/s, tg_3s = 1.88 t/s 18.49.301.686 I slot print_timing: id 0 | task 2878 | n_gen = 573, tg = 4.00 t/s, tg_3s = 4.32 t/s 18.49.302.095 I slot print_timing: id 3 | task 3259 | n_gen = 201, tg = 4.14 t/s, tg_3s = 4.32 t/s 18.50.353.527 I slot print_timing: id 1 | task 3331 | n_gen = 136, tg = 4.45 t/s, tg_3s = 4.76 t/s 18.52.456.731 I slot print_timing: id 0 | task 2878 | n_gen = 588, tg = 4.02 t/s, tg_3s = 4.75 t/s 18.52.457.124 I slot print_timing: id 3 | task 3259 | n_gen = 216, tg = 4.18 t/s, tg_3s = 4.75 t/s 18.53.507.197 I slot print_timing: id 1 | task 3331 | n_gen = 151, tg = 4.48 t/s, tg_3s = 4.76 t/s 18.55.609.991 I slot print_timing: id 0 | task 2878 | n_gen = 603, tg = 4.04 t/s, tg_3s = 4.76 t/s 18.55.610.403 I slot print_timing: id 3 | task 3259 | n_gen = 231, tg = 4.21 t/s, tg_3s = 4.76 t/s 18.56.661.923 I slot print_timing: id 1 | task 3331 | n_gen = 166, tg = 4.51 t/s, tg_3s = 4.75 t/s 18.58.763.895 I slot print_timing: id 0 | task 2878 | n_gen = 618, tg = 4.05 t/s, tg_3s = 4.76 t/s 18.58.764.322 I slot print_timing: id 3 | task 3259 | n_gen = 246, tg = 4.24 t/s, tg_3s = 4.76 t/s 18.59.815.781 I slot print_timing: id 1 | task 3331 | n_gen = 181, tg = 4.53 t/s, tg_3s = 4.76 t/s 19.01.917.768 I slot print_timing: id 0 | task 2878 | n_gen = 633, tg = 4.07 t/s, tg_3s = 4.76 t/s 19.01.918.215 I slot print_timing: id 3 | task 3259 | n_gen = 261, tg = 4.27 t/s, tg_3s = 4.76 t/s 19.02.968.910 I slot print_timing: id 1 | task 3331 | n_gen = 196, tg = 4.54 t/s, tg_3s = 4.76 t/s 19.05.070.573 I slot print_timing: id 0 | task 2878 | n_gen = 648, tg = 4.08 t/s, tg_3s = 4.76 t/s 19.05.071.009 I slot print_timing: id 3 | task 3259 | n_gen = 276, tg = 4.29 t/s, tg_3s = 4.76 t/s 19.06.122.292 I slot print_timing: id 1 | task 3331 | n_gen = 211, tg = 4.56 t/s, tg_3s = 4.76 t/s 19.07.594.586 I slot print_timing: id 2 | task 3450 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.80 t/s 19.08.225.104 I slot print_timing: id 0 | task 2878 | n_gen = 663, tg = 4.09 t/s, tg_3s = 4.76 t/s 19.08.225.512 I slot print_timing: id 3 | task 3259 | n_gen = 291, tg = 4.31 t/s, tg_3s = 4.76 t/s 19.08.435.981 I slot print_timing: id 3 | task 3259 | prompt eval time = 2458.25 ms / 144 tokens ( 17.07 ms per token, 58.58 tokens per second) 19.08.435.986 I slot print_timing: id 3 | task 3259 | eval time = 67447.08 ms / 292 tokens ( 231.78 ms per token, 4.31 tokens per second) 19.08.435.988 I slot print_timing: id 3 | task 3259 | total time = 69905.34 ms / 436 tokens 19.08.435.988 I slot print_timing: id 3 | task 3259 | graphs reused = 3001 19.08.435.989 I slot print_timing: id 3 | task 3259 | graph reallocs = 0 / 0 (same size) / (changed size) 19.08.436.033 I slot release: id 3 | task 3259 | stop processing: n_tokens = 1560, truncated = 0 19.08.635.169 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.735 19.08.635.201 I slot launch_slot_: id 3 | task 3557 | processing task, is_child = 0 19.10.349.612 I slot print_timing: id 1 | task 3331 | n_gen = 224, tg = 4.43 t/s, tg_3s = 3.08 t/s 19.10.747.629 I slot print_timing: id 2 | task 3450 | n_gen = 107, tg = 4.42 t/s, tg_3s = 2.22 t/s 19.11.380.867 I slot print_timing: id 0 | task 2878 | n_gen = 670, tg = 4.06 t/s, tg_3s = 2.22 t/s 19.13.483.573 I slot print_timing: id 1 | task 3331 | n_gen = 238, tg = 4.44 t/s, tg_3s = 4.47 t/s 19.13.904.211 I slot print_timing: id 2 | task 3450 | n_gen = 122, tg = 4.46 t/s, tg_3s = 4.75 t/s 19.14.533.325 I slot print_timing: id 0 | task 2878 | n_gen = 685, tg = 4.07 t/s, tg_3s = 4.76 t/s 19.16.636.698 I slot print_timing: id 1 | task 3331 | n_gen = 253, tg = 4.45 t/s, tg_3s = 4.76 t/s 19.17.056.653 I slot print_timing: id 2 | task 3450 | n_gen = 137, tg = 4.49 t/s, tg_3s = 4.76 t/s 19.17.687.686 I slot print_timing: id 0 | task 2878 | n_gen = 700, tg = 4.08 t/s, tg_3s = 4.76 t/s 19.19.790.604 I slot print_timing: id 1 | task 3331 | n_gen = 268, tg = 4.47 t/s, tg_3s = 4.76 t/s 19.20.210.965 I slot print_timing: id 2 | task 3450 | n_gen = 152, tg = 4.52 t/s, tg_3s = 4.76 t/s 19.20.841.755 I slot print_timing: id 0 | task 2878 | n_gen = 715, tg = 4.09 t/s, tg_3s = 4.76 t/s 19.22.944.201 I slot print_timing: id 1 | task 3331 | n_gen = 283, tg = 4.48 t/s, tg_3s = 4.76 t/s 19.23.364.769 I slot print_timing: id 2 | task 3450 | n_gen = 167, tg = 4.54 t/s, tg_3s = 4.76 t/s 19.23.995.196 I slot print_timing: id 0 | task 2878 | n_gen = 730, tg = 4.11 t/s, tg_3s = 4.76 t/s 19.26.098.708 I slot print_timing: id 1 | task 3331 | n_gen = 298, tg = 4.50 t/s, tg_3s = 4.76 t/s 19.26.519.716 I slot print_timing: id 2 | task 3450 | n_gen = 182, tg = 4.55 t/s, tg_3s = 4.75 t/s 19.27.149.987 I slot print_timing: id 0 | task 2878 | n_gen = 745, tg = 4.12 t/s, tg_3s = 4.75 t/s 19.29.043.368 I slot print_timing: id 2 | task 3450 | prompt eval time = 2271.39 ms / 115 tokens ( 19.75 ms per token, 50.63 tokens per second) 19.29.043.374 I slot print_timing: id 2 | task 3450 | eval time = 42267.39 ms / 194 tokens ( 219.00 ms per token, 4.57 tokens per second) 19.29.043.374 I slot print_timing: id 2 | task 3450 | total time = 44538.79 ms / 309 tokens 19.29.043.375 I slot print_timing: id 2 | task 3450 | graphs reused = 3087 19.29.043.375 I slot print_timing: id 2 | task 3450 | graph reallocs = 0 / 0 (same size) / (changed size) 19.29.043.423 I slot release: id 2 | task 3450 | stop processing: n_tokens = 1433, truncated = 0 19.29.329.528 I slot print_timing: id 1 | task 3331 | n_gen = 313, tg = 4.50 t/s, tg_3s = 4.64 t/s 19.29.329.684 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.800 19.29.329.713 I slot launch_slot_: id 2 | task 3648 | processing task, is_child = 0 19.30.775.390 I slot print_timing: id 0 | task 2878 | n_gen = 756, tg = 4.10 t/s, tg_3s = 3.03 t/s 19.32.523.048 I slot print_timing: id 1 | task 3331 | n_gen = 321, tg = 4.42 t/s, tg_3s = 2.51 t/s 19.33.154.228 I slot print_timing: id 3 | task 3557 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.46 t/s 19.33.784.961 I slot print_timing: id 0 | task 2878 | n_gen = 769, tg = 4.10 t/s, tg_3s = 4.32 t/s 19.35.677.664 I slot print_timing: id 1 | task 3331 | n_gen = 336, tg = 4.43 t/s, tg_3s = 4.75 t/s 19.36.308.904 I slot print_timing: id 3 | task 3557 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.75 t/s 19.36.939.093 I slot print_timing: id 0 | task 2878 | n_gen = 784, tg = 4.11 t/s, tg_3s = 4.76 t/s 19.38.831.658 I slot print_timing: id 1 | task 3331 | n_gen = 351, tg = 4.44 t/s, tg_3s = 4.76 t/s 19.39.463.295 I slot print_timing: id 3 | task 3557 | n_gen = 130, tg = 4.49 t/s, tg_3s = 4.76 t/s 19.40.093.669 I slot print_timing: id 0 | task 2878 | n_gen = 799, tg = 4.12 t/s, tg_3s = 4.75 t/s 19.41.994.714 I slot print_timing: id 1 | task 3331 | n_gen = 366, tg = 4.45 t/s, tg_3s = 4.74 t/s 19.42.627.398 I slot print_timing: id 3 | task 3557 | n_gen = 145, tg = 4.52 t/s, tg_3s = 4.74 t/s 19.43.048.546 I slot print_timing: id 2 | task 3648 | prompt eval time = 1928.75 ms / 81 tokens ( 23.81 ms per token, 42.00 tokens per second) 19.43.048.550 I slot print_timing: id 2 | task 3648 | eval time = 11790.08 ms / 57 tokens ( 210.54 ms per token, 4.75 tokens per second) 19.43.048.550 I slot print_timing: id 2 | task 3648 | total time = 13718.83 ms / 138 tokens 19.43.048.551 I slot print_timing: id 2 | task 3648 | graphs reused = 3141 19.43.048.551 I slot print_timing: id 2 | task 3648 | graph reallocs = 0 / 0 (same size) / (changed size) 19.43.048.594 I slot release: id 2 | task 3648 | stop processing: n_tokens = 1262, truncated = 0 19.43.333.816 I slot print_timing: id 0 | task 2878 | n_gen = 814, tg = 4.13 t/s, tg_3s = 4.63 t/s 19.43.334.102 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.908 19.43.334.134 I slot launch_slot_: id 2 | task 3708 | processing task, is_child = 0 19.45.103.618 I slot print_timing: id 1 | task 3331 | n_gen = 373, tg = 4.37 t/s, tg_3s = 2.25 t/s 19.45.800.924 I slot print_timing: id 3 | task 3557 | n_gen = 151, tg = 4.28 t/s, tg_3s = 1.89 t/s 19.46.432.662 I slot print_timing: id 0 | task 2878 | n_gen = 820, tg = 4.10 t/s, tg_3s = 1.94 t/s 19.48.119.111 I slot print_timing: id 1 | task 3331 | n_gen = 386, tg = 4.37 t/s, tg_3s = 4.31 t/s 19.48.963.155 I slot print_timing: id 3 | task 3557 | n_gen = 166, tg = 4.32 t/s, tg_3s = 4.74 t/s 19.49.595.776 I slot print_timing: id 0 | task 2878 | n_gen = 835, tg = 4.11 t/s, tg_3s = 4.74 t/s 19.51.282.315 I slot print_timing: id 1 | task 3331 | n_gen = 401, tg = 4.38 t/s, tg_3s = 4.74 t/s 19.52.125.637 I slot print_timing: id 3 | task 3557 | n_gen = 181, tg = 4.35 t/s, tg_3s = 4.74 t/s 19.52.757.699 I slot print_timing: id 0 | task 2878 | n_gen = 850, tg = 4.12 t/s, tg_3s = 4.74 t/s 19.54.444.440 I slot print_timing: id 1 | task 3331 | n_gen = 416, tg = 4.40 t/s, tg_3s = 4.74 t/s 19.55.287.648 I slot print_timing: id 3 | task 3557 | n_gen = 196, tg = 4.38 t/s, tg_3s = 4.74 t/s 19.55.919.926 I slot print_timing: id 0 | task 2878 | n_gen = 865, tg = 4.13 t/s, tg_3s = 4.74 t/s 19.57.606.824 I slot print_timing: id 1 | task 3331 | n_gen = 431, tg = 4.41 t/s, tg_3s = 4.74 t/s 19.58.450.985 I slot print_timing: id 3 | task 3557 | n_gen = 211, tg = 4.40 t/s, tg_3s = 4.74 t/s 19.59.082.421 I slot print_timing: id 0 | task 2878 | n_gen = 880, tg = 4.13 t/s, tg_3s = 4.74 t/s 20.00.769.930 I slot print_timing: id 1 | task 3331 | n_gen = 446, tg = 4.42 t/s, tg_3s = 4.74 t/s 20.01.614.313 I slot print_timing: id 3 | task 3557 | n_gen = 226, tg = 4.42 t/s, tg_3s = 4.74 t/s 20.02.246.552 I slot print_timing: id 0 | task 2878 | n_gen = 895, tg = 4.14 t/s, tg_3s = 4.74 t/s 20.03.934.816 I slot print_timing: id 1 | task 3331 | n_gen = 461, tg = 4.43 t/s, tg_3s = 4.74 t/s 20.04.779.030 I slot print_timing: id 3 | task 3557 | n_gen = 241, tg = 4.44 t/s, tg_3s = 4.74 t/s 20.05.411.288 I slot print_timing: id 0 | task 2878 | n_gen = 910, tg = 4.15 t/s, tg_3s = 4.74 t/s 20.06.466.527 I slot print_timing: id 2 | task 3708 | n_gen = 100, tg = 4.74 t/s, tg_3s = 4.79 t/s 20.07.098.542 I slot print_timing: id 1 | task 3331 | n_gen = 476, tg = 4.44 t/s, tg_3s = 4.74 t/s 20.07.942.888 I slot print_timing: id 3 | task 3557 | n_gen = 256, tg = 4.46 t/s, tg_3s = 4.74 t/s 20.08.153.402 I slot print_timing: id 2 | task 3708 | prompt eval time = 2253.52 ms / 104 tokens ( 21.67 ms per token, 46.15 tokens per second) 20.08.153.407 I slot print_timing: id 2 | task 3708 | eval time = 22565.74 ms / 108 tokens ( 210.89 ms per token, 4.74 tokens per second) 20.08.153.407 I slot print_timing: id 2 | task 3708 | total time = 24819.26 ms / 212 tokens 20.08.153.408 I slot print_timing: id 2 | task 3708 | graphs reused = 3247 20.08.153.408 I slot print_timing: id 2 | task 3708 | graph reallocs = 0 / 0 (same size) / (changed size) 20.08.153.458 I slot release: id 2 | task 3708 | stop processing: n_tokens = 1336, truncated = 0 20.08.439.674 I slot print_timing: id 0 | task 2878 | n_gen = 924, tg = 4.16 t/s, tg_3s = 4.62 t/s 20.08.440.023 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.858 20.08.440.074 I slot launch_slot_: id 2 | task 3819 | processing task, is_child = 0 20.10.247.454 I slot print_timing: id 1 | task 3331 | n_gen = 483, tg = 4.37 t/s, tg_3s = 2.22 t/s 20.10.945.318 I slot print_timing: id 3 | task 3557 | n_gen = 261, tg = 4.32 t/s, tg_3s = 1.67 t/s 20.11.577.766 I slot print_timing: id 0 | task 2878 | n_gen = 930, tg = 4.13 t/s, tg_3s = 1.91 t/s 20.13.264.718 I slot print_timing: id 1 | task 3331 | n_gen = 496, tg = 4.37 t/s, tg_3s = 4.31 t/s 20.14.108.575 I slot print_timing: id 3 | task 3557 | n_gen = 276, tg = 4.34 t/s, tg_3s = 4.74 t/s 20.14.741.425 I slot print_timing: id 0 | task 2878 | n_gen = 945, tg = 4.14 t/s, tg_3s = 4.74 t/s 20.16.428.530 I slot print_timing: id 1 | task 3331 | n_gen = 511, tg = 4.38 t/s, tg_3s = 4.74 t/s 20.17.272.391 I slot print_timing: id 3 | task 3557 | n_gen = 291, tg = 4.36 t/s, tg_3s = 4.74 t/s 20.17.905.437 I slot print_timing: id 0 | task 2878 | n_gen = 960, tg = 4.14 t/s, tg_3s = 4.74 t/s 20.19.594.071 I slot print_timing: id 1 | task 3331 | n_gen = 526, tg = 4.39 t/s, tg_3s = 4.74 t/s 20.20.439.219 I slot print_timing: id 3 | task 3557 | n_gen = 306, tg = 4.38 t/s, tg_3s = 4.74 t/s 20.21.072.086 I slot print_timing: id 0 | task 2878 | n_gen = 975, tg = 4.15 t/s, tg_3s = 4.74 t/s 20.22.761.145 I slot print_timing: id 1 | task 3331 | n_gen = 541, tg = 4.40 t/s, tg_3s = 4.74 t/s 20.23.604.923 I slot print_timing: id 3 | task 3557 | n_gen = 321, tg = 4.39 t/s, tg_3s = 4.74 t/s 20.24.237.728 I slot print_timing: id 0 | task 2878 | n_gen = 990, tg = 4.16 t/s, tg_3s = 4.74 t/s 20.25.925.999 I slot print_timing: id 1 | task 3331 | n_gen = 556, tg = 4.41 t/s, tg_3s = 4.74 t/s 20.26.770.092 I slot print_timing: id 3 | task 3557 | n_gen = 336, tg = 4.41 t/s, tg_3s = 4.74 t/s 20.27.402.708 I slot print_timing: id 0 | task 2878 | n_gen = 1005, tg = 4.17 t/s, tg_3s = 4.74 t/s 20.27.402.858 I slot print_timing: id 1 | task 3331 | prompt eval time = 2774.81 ms / 158 tokens ( 17.56 ms per token, 56.94 tokens per second) 20.27.402.860 I slot print_timing: id 1 | task 3331 | eval time = 127355.63 ms / 563 tokens ( 226.61 ms per token, 4.41 tokens per second) 20.27.402.860 I slot print_timing: id 1 | task 3331 | total time = 130130.44 ms / 721 tokens 20.27.402.861 I slot print_timing: id 1 | task 3331 | graphs reused = 3325 20.27.402.861 I slot print_timing: id 1 | task 3331 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.402.910 I slot release: id 1 | task 3331 | stop processing: n_tokens = 1845, truncated = 0 20.27.688.841 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.621 20.27.688.877 I slot launch_slot_: id 1 | task 3902 | processing task, is_child = 0 20.30.083.795 I slot print_timing: id 3 | task 3557 | n_gen = 342, tg = 4.30 t/s, tg_3s = 1.81 t/s 20.30.507.778 I slot print_timing: id 0 | task 2878 | n_gen = 1010, tg = 4.13 t/s, tg_3s = 1.61 t/s 20.33.249.951 I slot print_timing: id 3 | task 3557 | n_gen = 357, tg = 4.32 t/s, tg_3s = 4.74 t/s 20.33.460.722 I slot print_timing: id 0 | task 2878 | prompt eval time = 2081.50 ms / 124 tokens ( 16.79 ms per token, 59.57 tokens per second) 20.33.460.724 I slot print_timing: id 0 | task 2878 | eval time = 246991.51 ms / 1024 tokens ( 241.44 ms per token, 4.14 tokens per second) 20.33.460.724 I slot print_timing: id 0 | task 2878 | total time = 249073.01 ms / 1148 tokens 20.33.460.725 I slot print_timing: id 0 | task 2878 | graphs reused = 3340 20.33.460.725 I slot print_timing: id 0 | task 2878 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.460.771 I slot release: id 0 | task 2878 | stop processing: n_tokens = 2272, truncated = 0 20.33.660.694 I slot print_timing: id 2 | task 3819 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 20.33.660.851 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.504 20.33.660.889 I slot launch_slot_: id 0 | task 3922 | processing task, is_child = 0 20.36.379.278 I slot print_timing: id 3 | task 3557 | n_gen = 364, tg = 4.24 t/s, tg_3s = 2.24 t/s 20.36.799.477 I slot print_timing: id 2 | task 3819 | n_gen = 107, tg = 4.07 t/s, tg_3s = 2.23 t/s 20.39.528.284 I slot print_timing: id 3 | task 3557 | n_gen = 379, tg = 4.26 t/s, tg_3s = 4.76 t/s 20.39.948.152 I slot print_timing: id 2 | task 3819 | n_gen = 122, tg = 4.14 t/s, tg_3s = 4.76 t/s 20.42.678.320 I slot print_timing: id 3 | task 3557 | n_gen = 394, tg = 4.27 t/s, tg_3s = 4.76 t/s 20.42.888.140 I slot print_timing: id 2 | task 3819 | prompt eval time = 2291.66 ms / 125 tokens ( 18.33 ms per token, 54.55 tokens per second) 20.42.888.145 I slot print_timing: id 2 | task 3819 | eval time = 32156.40 ms / 136 tokens ( 238.20 ms per token, 4.20 tokens per second) 20.42.888.146 I slot print_timing: id 2 | task 3819 | total time = 34448.06 ms / 261 tokens 20.42.888.146 I slot print_timing: id 2 | task 3819 | graphs reused = 3374 20.42.888.147 I slot print_timing: id 2 | task 3819 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.888.190 I slot release: id 2 | task 3819 | stop processing: n_tokens = 1385, truncated = 0 20.43.172.565 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.827 20.43.172.606 I slot launch_slot_: id 2 | task 3960 | processing task, is_child = 0 20.45.871.964 I slot print_timing: id 3 | task 3557 | n_gen = 400, tg = 4.19 t/s, tg_3s = 1.88 t/s 20.49.022.399 I slot print_timing: id 3 | task 3557 | n_gen = 415, tg = 4.21 t/s, tg_3s = 4.76 t/s 20.52.172.254 I slot print_timing: id 3 | task 3557 | n_gen = 430, tg = 4.23 t/s, tg_3s = 4.76 t/s 20.54.484.334 I slot print_timing: id 1 | task 3902 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.10 t/s 20.55.322.738 I slot print_timing: id 3 | task 3557 | n_gen = 445, tg = 4.25 t/s, tg_3s = 4.76 t/s 20.57.634.233 I slot print_timing: id 1 | task 3902 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.76 t/s 20.58.474.827 I slot print_timing: id 0 | task 3922 | n_gen = 100, tg = 4.36 t/s, tg_3s = 4.40 t/s 20.58.475.231 I slot print_timing: id 3 | task 3557 | n_gen = 460, tg = 4.26 t/s, tg_3s = 4.76 t/s 21.00.576.042 I slot print_timing: id 3 | task 3557 | prompt eval time = 2112.66 ms / 128 tokens ( 16.51 ms per token, 60.59 tokens per second) 21.00.576.048 I slot print_timing: id 3 | task 3557 | eval time = 109828.17 ms / 470 tokens ( 234.18 ms per token, 4.27 tokens per second) 21.00.576.048 I slot print_timing: id 3 | task 3557 | total time = 111940.83 ms / 598 tokens 21.00.576.049 I slot print_timing: id 3 | task 3557 | graphs reused = 3445 21.00.576.049 I slot print_timing: id 3 | task 3557 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.576.093 I slot release: id 3 | task 3557 | stop processing: n_tokens = 1722, truncated = 0 21.00.774.666 I slot print_timing: id 1 | task 3902 | n_gen = 130, tg = 4.20 t/s, tg_3s = 4.78 t/s 21.00.774.821 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.667 21.00.774.852 I slot launch_slot_: id 3 | task 4036 | processing task, is_child = 0 21.02.472.807 I slot print_timing: id 0 | task 3922 | n_gen = 112, tg = 4.15 t/s, tg_3s = 3.00 t/s 21.03.922.164 I slot print_timing: id 1 | task 3902 | n_gen = 137, tg = 4.02 t/s, tg_3s = 2.22 t/s 21.05.601.313 I slot print_timing: id 0 | task 3922 | n_gen = 126, tg = 4.19 t/s, tg_3s = 4.47 t/s 21.07.071.514 I slot print_timing: id 1 | task 3902 | n_gen = 152, tg = 4.08 t/s, tg_3s = 4.76 t/s 21.07.911.992 I slot print_timing: id 2 | task 3960 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 21.08.751.586 I slot print_timing: id 0 | task 3922 | n_gen = 141, tg = 4.24 t/s, tg_3s = 4.76 t/s 21.10.221.682 I slot print_timing: id 1 | task 3902 | n_gen = 167, tg = 4.14 t/s, tg_3s = 4.76 t/s 21.11.061.857 I slot print_timing: id 2 | task 3960 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.76 t/s 21.11.901.618 I slot print_timing: id 0 | task 3922 | n_gen = 156, tg = 4.29 t/s, tg_3s = 4.76 t/s 21.13.371.551 I slot print_timing: id 1 | task 3902 | n_gen = 182, tg = 4.18 t/s, tg_3s = 4.76 t/s 21.14.212.137 I slot print_timing: id 2 | task 3960 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.76 t/s 21.15.052.146 I slot print_timing: id 0 | task 3922 | n_gen = 171, tg = 4.33 t/s, tg_3s = 4.76 t/s 21.16.521.916 I slot print_timing: id 1 | task 3902 | n_gen = 197, tg = 4.22 t/s, tg_3s = 4.76 t/s 21.17.362.096 I slot print_timing: id 2 | task 3960 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.76 t/s 21.18.201.995 I slot print_timing: id 0 | task 3922 | prompt eval time = 2085.34 ms / 126 tokens ( 16.55 ms per token, 60.42 tokens per second) 21.18.202.000 I slot print_timing: id 0 | task 3922 | eval time = 42455.76 ms / 186 tokens ( 229.49 ms per token, 4.36 tokens per second) 21.18.202.000 I slot print_timing: id 0 | task 3922 | total time = 44541.10 ms / 312 tokens 21.18.202.001 I slot print_timing: id 0 | task 3922 | graphs reused = 3517 21.18.202.001 I slot print_timing: id 0 | task 3922 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.202.053 I slot release: id 0 | task 3922 | stop processing: n_tokens = 1436, truncated = 0 21.18.401.991 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.798 21.18.402.021 I slot launch_slot_: id 0 | task 4113 | processing task, is_child = 0 21.19.752.068 I slot print_timing: id 1 | task 3902 | n_gen = 207, tg = 4.15 t/s, tg_3s = 3.10 t/s 21.20.559.703 I slot print_timing: id 2 | task 3960 | n_gen = 154, tg = 4.36 t/s, tg_3s = 2.81 t/s 21.22.869.835 I slot print_timing: id 1 | task 3902 | n_gen = 221, tg = 4.17 t/s, tg_3s = 4.49 t/s 21.23.709.641 I slot print_timing: id 2 | task 3960 | n_gen = 169, tg = 4.39 t/s, tg_3s = 4.76 t/s 21.24.969.709 I slot print_timing: id 3 | task 4036 | n_gen = 100, tg = 4.48 t/s, tg_3s = 4.52 t/s 21.26.017.913 I slot print_timing: id 1 | task 3902 | n_gen = 236, tg = 4.20 t/s, tg_3s = 4.76 t/s 21.26.858.233 I slot print_timing: id 2 | task 3960 | n_gen = 184, tg = 4.42 t/s, tg_3s = 4.76 t/s 21.28.118.106 I slot print_timing: id 3 | task 4036 | n_gen = 115, tg = 4.52 t/s, tg_3s = 4.76 t/s 21.29.167.985 I slot print_timing: id 1 | task 3902 | n_gen = 251, tg = 4.23 t/s, tg_3s = 4.76 t/s 21.30.008.204 I slot print_timing: id 2 | task 3960 | n_gen = 199, tg = 4.44 t/s, tg_3s = 4.76 t/s 21.30.008.372 I slot print_timing: id 3 | task 4036 | prompt eval time = 2095.21 ms / 108 tokens ( 19.40 ms per token, 51.55 tokens per second) 21.30.008.376 I slot print_timing: id 3 | task 4036 | eval time = 27138.30 ms / 124 tokens ( 220.64 ms per token, 4.53 tokens per second) 21.30.008.377 I slot print_timing: id 3 | task 4036 | total time = 29233.52 ms / 232 tokens 21.30.008.377 I slot print_timing: id 3 | task 4036 | graphs reused = 3564 21.30.008.377 I slot print_timing: id 3 | task 4036 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.008.423 I slot release: id 3 | task 4036 | stop processing: n_tokens = 1356, truncated = 0 21.30.207.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.845 21.30.207.397 I slot launch_slot_: id 3 | task 4164 | processing task, is_child = 0 21.32.616.678 I slot print_timing: id 1 | task 3902 | n_gen = 257, tg = 4.09 t/s, tg_3s = 1.74 t/s 21.33.014.003 I slot print_timing: id 2 | task 3960 | n_gen = 202, tg = 4.23 t/s, tg_3s = 1.00 t/s 21.35.745.949 I slot print_timing: id 1 | task 3902 | n_gen = 271, tg = 4.11 t/s, tg_3s = 4.47 t/s 21.36.166.391 I slot print_timing: id 2 | task 3960 | n_gen = 217, tg = 4.26 t/s, tg_3s = 4.76 t/s 21.38.897.223 I slot print_timing: id 1 | task 3902 | n_gen = 286, tg = 4.14 t/s, tg_3s = 4.76 t/s 21.39.107.281 I slot print_timing: id 0 | task 4113 | prompt eval time = 1735.96 ms / 100 tokens ( 17.36 ms per token, 57.60 tokens per second) 21.39.107.287 I slot print_timing: id 0 | task 4113 | eval time = 18969.29 ms / 80 tokens ( 240.12 ms per token, 4.16 tokens per second) 21.39.107.287 I slot print_timing: id 0 | task 4113 | total time = 20705.25 ms / 180 tokens 21.39.107.288 I slot print_timing: id 0 | task 4113 | graphs reused = 3592 21.39.107.288 I slot print_timing: id 0 | task 4113 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.107.335 I slot release: id 0 | task 4113 | stop processing: n_tokens = 1304, truncated = 0 21.39.306.842 I slot print_timing: id 2 | task 3960 | n_gen = 232, tg = 4.29 t/s, tg_3s = 4.78 t/s 21.39.306.998 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.879 21.39.307.025 I slot launch_slot_: id 0 | task 4197 | processing task, is_child = 0 21.42.099.577 I slot print_timing: id 1 | task 3902 | n_gen = 295, tg = 4.08 t/s, tg_3s = 2.81 t/s 21.42.309.937 I slot print_timing: id 2 | task 3960 | n_gen = 240, tg = 4.20 t/s, tg_3s = 2.66 t/s 21.45.253.254 I slot print_timing: id 1 | task 3902 | n_gen = 310, tg = 4.11 t/s, tg_3s = 4.76 t/s 21.45.463.294 I slot print_timing: id 2 | task 3960 | n_gen = 255, tg = 4.23 t/s, tg_3s = 4.76 t/s 21.48.404.885 I slot print_timing: id 1 | task 3902 | n_gen = 325, tg = 4.14 t/s, tg_3s = 4.76 t/s 21.48.614.962 I slot print_timing: id 2 | task 3960 | n_gen = 270, tg = 4.26 t/s, tg_3s = 4.76 t/s 21.51.556.335 I slot print_timing: id 1 | task 3902 | n_gen = 340, tg = 4.16 t/s, tg_3s = 4.76 t/s 21.51.766.611 I slot print_timing: id 2 | task 3960 | n_gen = 285, tg = 4.28 t/s, tg_3s = 4.76 t/s 21.53.237.276 I slot print_timing: id 2 | task 3960 | prompt eval time = 2276.76 ms / 125 tokens ( 18.21 ms per token, 54.90 tokens per second) 21.53.237.279 I slot print_timing: id 2 | task 3960 | eval time = 67787.90 ms / 292 tokens ( 232.95 ms per token, 4.29 tokens per second) 21.53.237.279 I slot print_timing: id 2 | task 3960 | total time = 70064.66 ms / 417 tokens 21.53.237.280 I slot print_timing: id 2 | task 3960 | graphs reused = 3649 21.53.237.280 I slot print_timing: id 2 | task 3960 | graph reallocs = 0 / 0 (same size) / (changed size) 21.53.237.329 I slot release: id 2 | task 3960 | stop processing: n_tokens = 1541, truncated = 0 21.53.522.335 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.744 21.53.522.371 I slot launch_slot_: id 2 | task 4259 | processing task, is_child = 0 21.54.971.027 I slot print_timing: id 1 | task 3902 | n_gen = 350, tg = 4.11 t/s, tg_3s = 2.93 t/s 21.56.717.331 I slot print_timing: id 3 | task 4164 | n_gen = 100, tg = 4.18 t/s, tg_3s = 4.22 t/s 21.57.977.761 I slot print_timing: id 1 | task 3902 | n_gen = 363, tg = 4.12 t/s, tg_3s = 4.32 t/s 21.59.868.768 I slot print_timing: id 3 | task 4164 | n_gen = 115, tg = 4.25 t/s, tg_3s = 4.76 t/s 22.01.128.936 I slot print_timing: id 0 | task 4197 | prompt eval time = 1740.05 ms / 89 tokens ( 19.55 ms per token, 51.15 tokens per second) 22.01.128.941 I slot print_timing: id 0 | task 4197 | eval time = 20081.86 ms / 89 tokens ( 228.20 ms per token, 4.38 tokens per second) 22.01.128.942 I slot print_timing: id 0 | task 4197 | total time = 21821.90 ms / 178 tokens 22.01.128.943 I slot print_timing: id 0 | task 4197 | graphs reused = 3675 22.01.128.943 I slot print_timing: id 0 | task 4197 | graph reallocs = 0 / 0 (same size) / (changed size) 22.01.128.986 I slot release: id 0 | task 4197 | stop processing: n_tokens = 1302, truncated = 0 22.01.129.136 I slot print_timing: id 1 | task 3902 | n_gen = 378, tg = 4.14 t/s, tg_3s = 4.76 t/s 22.01.328.467 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.880 22.01.328.501 I slot launch_slot_: id 0 | task 4290 | processing task, is_child = 0 22.03.017.738 I slot print_timing: id 3 | task 4164 | n_gen = 123, tg = 4.07 t/s, tg_3s = 2.54 t/s 22.04.246.032 I slot print_timing: id 1 | task 3902 | n_gen = 385, tg = 4.08 t/s, tg_3s = 2.25 t/s 22.05.506.810 I slot print_timing: id 3 | task 4164 | prompt eval time = 2806.79 ms / 171 tokens ( 16.41 ms per token, 60.92 tokens per second) 22.05.506.816 I slot print_timing: id 3 | task 4164 | eval time = 32492.62 ms / 134 tokens ( 244.31 ms per token, 4.09 tokens per second) 22.05.506.816 I slot print_timing: id 3 | task 4164 | total time = 35299.40 ms / 305 tokens 22.05.506.817 I slot print_timing: id 3 | task 4164 | graphs reused = 3685 22.05.506.817 I slot print_timing: id 3 | task 4164 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.506.870 I slot release: id 3 | task 4164 | stop processing: n_tokens = 1429, truncated = 0 22.05.706.166 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.802 22.05.706.201 I slot launch_slot_: id 3 | task 4304 | processing task, is_child = 0 22.07.478.179 I slot print_timing: id 1 | task 3902 | n_gen = 394, tg = 4.04 t/s, tg_3s = 2.78 t/s 22.10.630.444 I slot print_timing: id 1 | task 3902 | n_gen = 409, tg = 4.06 t/s, tg_3s = 4.76 t/s 22.11.050.558 I slot print_timing: id 2 | task 4259 | prompt eval time = 1931.41 ms / 82 tokens ( 23.55 ms per token, 42.46 tokens per second) 22.11.050.564 I slot print_timing: id 2 | task 4259 | eval time = 15596.77 ms / 61 tokens ( 259.95 ms per token, 3.85 tokens per second) 22.11.050.564 I slot print_timing: id 2 | task 4259 | total time = 17528.18 ms / 143 tokens 22.11.050.565 I slot print_timing: id 2 | task 4259 | graphs reused = 3701 22.11.050.565 I slot print_timing: id 2 | task 4259 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.050.610 I slot release: id 2 | task 4259 | stop processing: n_tokens = 1267, truncated = 0 22.11.335.894 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.904 22.11.335.928 I slot launch_slot_: id 2 | task 4325 | processing task, is_child = 0 22.13.809.978 I slot print_timing: id 1 | task 3902 | n_gen = 415, tg = 3.99 t/s, tg_3s = 1.89 t/s 22.16.959.197 I slot print_timing: id 1 | task 3902 | n_gen = 430, tg = 4.01 t/s, tg_3s = 4.76 t/s 22.20.108.593 I slot print_timing: id 1 | task 3902 | n_gen = 445, tg = 4.04 t/s, tg_3s = 4.76 t/s 22.21.578.578 I slot print_timing: id 0 | task 4290 | prompt eval time = 2074.35 ms / 114 tokens ( 18.20 ms per token, 54.96 tokens per second) 22.21.578.581 I slot print_timing: id 0 | task 4290 | eval time = 18175.72 ms / 72 tokens ( 256.00 ms per token, 3.91 tokens per second) 22.21.578.582 I slot print_timing: id 0 | task 4290 | total time = 20250.07 ms / 186 tokens 22.21.578.582 I slot print_timing: id 0 | task 4290 | graphs reused = 3738 22.21.578.583 I slot print_timing: id 0 | task 4290 | graph reallocs = 0 / 0 (same size) / (changed size) 22.21.578.631 I slot release: id 0 | task 4290 | stop processing: n_tokens = 1310, truncated = 0 22.21.777.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.875 22.21.777.936 I slot launch_slot_: id 0 | task 4367 | processing task, is_child = 0 22.23.138.695 I slot print_timing: id 1 | task 3902 | n_gen = 454, tg = 4.01 t/s, tg_3s = 2.97 t/s 22.24.998.268 I slot print_timing: id 3 | task 4304 | prompt eval time = 1772.31 ms / 98 tokens ( 18.08 ms per token, 55.30 tokens per second) 22.24.998.273 I slot print_timing: id 3 | task 4304 | eval time = 17519.75 ms / 69 tokens ( 257.64 ms per token, 3.88 tokens per second) 22.24.998.274 I slot print_timing: id 3 | task 4304 | total time = 19292.06 ms / 167 tokens 22.24.998.274 I slot print_timing: id 3 | task 4304 | graphs reused = 3745 22.24.998.275 I slot print_timing: id 3 | task 4304 | graph reallocs = 0 / 0 (same size) / (changed size) 22.24.998.318 I slot release: id 3 | task 4304 | stop processing: n_tokens = 1291, truncated = 0 22.25.196.967 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.888 22.25.196.997 I slot launch_slot_: id 3 | task 4378 | processing task, is_child = 0 22.26.897.843 I slot print_timing: id 1 | task 3902 | n_gen = 464, tg = 3.96 t/s, tg_3s = 2.66 t/s 22.30.026.365 I slot print_timing: id 1 | task 3902 | n_gen = 478, tg = 3.98 t/s, tg_3s = 4.47 t/s 22.33.176.317 I slot print_timing: id 1 | task 3902 | n_gen = 493, tg = 4.00 t/s, tg_3s = 4.76 t/s 22.36.326.733 I slot print_timing: id 1 | task 3902 | n_gen = 508, tg = 4.02 t/s, tg_3s = 4.76 t/s 22.37.377.278 I slot print_timing: id 2 | task 4325 | n_gen = 100, tg = 4.16 t/s, tg_3s = 4.21 t/s 22.39.478.508 I slot print_timing: id 1 | task 3902 | n_gen = 523, tg = 4.03 t/s, tg_3s = 4.76 t/s 22.40.529.056 I slot print_timing: id 2 | task 4325 | n_gen = 115, tg = 4.23 t/s, tg_3s = 4.76 t/s 22.42.630.040 I slot print_timing: id 1 | task 3902 | n_gen = 538, tg = 4.05 t/s, tg_3s = 4.76 t/s 22.43.681.205 I slot print_timing: id 2 | task 4325 | n_gen = 130, tg = 4.29 t/s, tg_3s = 4.76 t/s 22.45.782.476 I slot print_timing: id 1 | task 3902 | n_gen = 553, tg = 4.07 t/s, tg_3s = 4.76 t/s 22.45.992.635 I slot print_timing: id 0 | task 4367 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 22.46.833.755 I slot print_timing: id 2 | task 4325 | n_gen = 145, tg = 4.33 t/s, tg_3s = 4.76 t/s 22.48.095.012 I slot print_timing: id 3 | task 4378 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 22.48.938.192 I slot print_timing: id 1 | task 3902 | n_gen = 568, tg = 4.08 t/s, tg_3s = 4.75 t/s 22.49.148.174 I slot print_timing: id 0 | task 4367 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 22.49.989.331 I slot print_timing: id 2 | task 4325 | n_gen = 160, tg = 4.37 t/s, tg_3s = 4.75 t/s 22.51.250.563 I slot print_timing: id 3 | task 4378 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.75 t/s 22.52.090.923 I slot print_timing: id 1 | task 3902 | n_gen = 583, tg = 4.10 t/s, tg_3s = 4.76 t/s 22.52.300.956 I slot print_timing: id 0 | task 4367 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.76 t/s 22.53.142.164 I slot print_timing: id 2 | task 4325 | n_gen = 175, tg = 4.40 t/s, tg_3s = 4.76 t/s 22.54.403.778 I slot print_timing: id 3 | task 4378 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 22.55.244.391 I slot print_timing: id 1 | task 3902 | n_gen = 598, tg = 4.11 t/s, tg_3s = 4.76 t/s 22.55.454.311 I slot print_timing: id 0 | task 4367 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.76 t/s 22.55.874.648 I slot print_timing: id 0 | task 4367 | prompt eval time = 1747.18 ms / 97 tokens ( 18.01 ms per token, 55.52 tokens per second) 22.55.874.653 I slot print_timing: id 0 | task 4367 | eval time = 32349.52 ms / 147 tokens ( 221.57 ms per token, 4.51 tokens per second) 22.55.874.654 I slot print_timing: id 0 | task 4367 | total time = 34096.70 ms / 244 tokens 22.55.874.654 I slot print_timing: id 0 | task 4367 | graphs reused = 3879 22.55.874.655 I slot print_timing: id 0 | task 4367 | graph reallocs = 0 / 0 (same size) / (changed size) 22.55.874.697 I slot release: id 0 | task 4367 | stop processing: n_tokens = 1368, truncated = 0 22.56.074.899 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.838 22.56.074.932 I slot launch_slot_: id 0 | task 4518 | processing task, is_child = 0 22.57.768.699 I slot print_timing: id 2 | task 4325 | n_gen = 190, tg = 4.28 t/s, tg_3s = 3.24 t/s 22.57.768.903 I slot print_timing: id 3 | task 4378 | n_gen = 139, tg = 4.53 t/s, tg_3s = 2.67 t/s 22.58.368.228 I slot print_timing: id 1 | task 3902 | n_gen = 605, tg = 4.07 t/s, tg_3s = 2.24 t/s 23.00.890.737 I slot print_timing: id 2 | task 4325 | n_gen = 204, tg = 4.29 t/s, tg_3s = 4.48 t/s 23.00.890.885 I slot print_timing: id 3 | task 4378 | n_gen = 153, tg = 4.52 t/s, tg_3s = 4.48 t/s 23.01.521.088 I slot print_timing: id 1 | task 3902 | n_gen = 620, tg = 4.09 t/s, tg_3s = 4.76 t/s 23.04.043.278 I slot print_timing: id 2 | task 4325 | n_gen = 219, tg = 4.32 t/s, tg_3s = 4.76 t/s 23.04.043.431 I slot print_timing: id 3 | task 4378 | n_gen = 168, tg = 4.54 t/s, tg_3s = 4.76 t/s 23.04.673.417 I slot print_timing: id 1 | task 3902 | n_gen = 635, tg = 4.10 t/s, tg_3s = 4.76 t/s 23.07.196.364 I slot print_timing: id 2 | task 4325 | n_gen = 234, tg = 4.35 t/s, tg_3s = 4.76 t/s 23.07.196.517 I slot print_timing: id 3 | task 4378 | n_gen = 183, tg = 4.56 t/s, tg_3s = 4.76 t/s 23.07.827.054 I slot print_timing: id 1 | task 3902 | n_gen = 650, tg = 4.11 t/s, tg_3s = 4.76 t/s 23.10.351.011 I slot print_timing: id 2 | task 4325 | n_gen = 249, tg = 4.37 t/s, tg_3s = 4.75 t/s 23.10.351.164 I slot print_timing: id 3 | task 4378 | n_gen = 198, tg = 4.58 t/s, tg_3s = 4.75 t/s 23.10.981.895 I slot print_timing: id 1 | task 3902 | n_gen = 665, tg = 4.13 t/s, tg_3s = 4.75 t/s 23.13.506.026 I slot print_timing: id 2 | task 4325 | n_gen = 264, tg = 4.39 t/s, tg_3s = 4.75 t/s 23.13.506.183 I slot print_timing: id 3 | task 4378 | n_gen = 213, tg = 4.59 t/s, tg_3s = 4.75 t/s 23.14.137.352 I slot print_timing: id 1 | task 3902 | n_gen = 680, tg = 4.14 t/s, tg_3s = 4.75 t/s 23.16.030.360 I slot print_timing: id 3 | task 4378 | prompt eval time = 2096.78 ms / 113 tokens ( 18.56 ms per token, 53.89 tokens per second) 23.16.030.365 I slot print_timing: id 3 | task 4378 | eval time = 48736.57 ms / 225 tokens ( 217.57 ms per token, 4.60 tokens per second) 23.16.030.365 I slot print_timing: id 3 | task 4378 | total time = 50833.35 ms / 338 tokens 23.16.030.366 I slot print_timing: id 3 | task 4378 | graphs reused = 3964 23.16.030.366 I slot print_timing: id 3 | task 4378 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.030.411 I slot release: id 3 | task 4378 | stop processing: n_tokens = 1462, truncated = 0 23.16.229.946 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.784 23.16.229.984 I slot launch_slot_: id 3 | task 4607 | processing task, is_child = 0 23.18.282.750 I slot print_timing: id 1 | task 3902 | n_gen = 691, tg = 4.10 t/s, tg_3s = 2.65 t/s 23.18.282.971 I slot print_timing: id 2 | task 4325 | n_gen = 278, tg = 4.28 t/s, tg_3s = 2.93 t/s 23.20.997.015 I slot print_timing: id 0 | task 4518 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.38 t/s 23.21.207.425 I slot print_timing: id 2 | task 4325 | prompt eval time = 2261.61 ms / 109 tokens ( 20.75 ms per token, 48.20 tokens per second) 23.21.207.427 I slot print_timing: id 2 | task 4325 | eval time = 67609.88 ms / 291 tokens ( 233.14 ms per token, 4.29 tokens per second) 23.21.207.428 I slot print_timing: id 2 | task 4325 | total time = 69871.49 ms / 400 tokens 23.21.207.428 I slot print_timing: id 2 | task 4325 | graphs reused = 3975 23.21.207.429 I slot print_timing: id 2 | task 4325 | graph reallocs = 0 / 0 (same size) / (changed size) 23.21.207.477 I slot release: id 2 | task 4325 | stop processing: n_tokens = 1524, truncated = 0 23.21.493.022 I slot print_timing: id 1 | task 3902 | n_gen = 705, tg = 4.11 t/s, tg_3s = 4.36 t/s 23.21.493.174 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.752 23.21.493.202 I slot launch_slot_: id 2 | task 4623 | processing task, is_child = 0 23.24.184.680 I slot print_timing: id 0 | task 4518 | n_gen = 106, tg = 4.03 t/s, tg_3s = 1.88 t/s 23.24.604.931 I slot print_timing: id 1 | task 3902 | n_gen = 711, tg = 4.07 t/s, tg_3s = 1.93 t/s 23.27.337.044 I slot print_timing: id 0 | task 4518 | n_gen = 121, tg = 4.11 t/s, tg_3s = 4.76 t/s 23.27.757.587 I slot print_timing: id 1 | task 3902 | n_gen = 726, tg = 4.08 t/s, tg_3s = 4.76 t/s 23.30.490.395 I slot print_timing: id 0 | task 4518 | n_gen = 136, tg = 4.18 t/s, tg_3s = 4.76 t/s 23.30.911.238 I slot print_timing: id 1 | task 3902 | n_gen = 741, tg = 4.09 t/s, tg_3s = 4.76 t/s 23.33.013.856 I slot print_timing: id 0 | task 4518 | prompt eval time = 2080.50 ms / 119 tokens ( 17.48 ms per token, 57.20 tokens per second) 23.33.013.860 I slot print_timing: id 0 | task 4518 | eval time = 34858.41 ms / 148 tokens ( 237.13 ms per token, 4.22 tokens per second) 23.33.013.861 I slot print_timing: id 0 | task 4518 | total time = 36938.92 ms / 267 tokens 23.33.013.861 I slot print_timing: id 0 | task 4518 | graphs reused = 4018 23.33.013.861 I slot print_timing: id 0 | task 4518 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.013.905 I slot release: id 0 | task 4518 | stop processing: n_tokens = 1391, truncated = 0 23.33.213.666 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.825 23.33.213.704 I slot launch_slot_: id 0 | task 4671 | processing task, is_child = 0 23.34.896.199 I slot print_timing: id 1 | task 3902 | n_gen = 753, tg = 4.07 t/s, tg_3s = 3.01 t/s 23.38.017.626 I slot print_timing: id 1 | task 3902 | n_gen = 767, tg = 4.08 t/s, tg_3s = 4.49 t/s 23.41.170.453 I slot print_timing: id 1 | task 3902 | n_gen = 782, tg = 4.09 t/s, tg_3s = 4.76 t/s 23.43.062.870 I slot print_timing: id 3 | task 4607 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.10 t/s 23.44.323.615 I slot print_timing: id 1 | task 3902 | n_gen = 797, tg = 4.10 t/s, tg_3s = 4.76 t/s 23.46.215.747 I slot print_timing: id 2 | task 4623 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 23.46.215.894 I slot print_timing: id 3 | task 4607 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.76 t/s 23.47.477.357 I slot print_timing: id 1 | task 3902 | n_gen = 812, tg = 4.11 t/s, tg_3s = 4.76 t/s 23.49.369.416 I slot print_timing: id 2 | task 4623 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.76 t/s 23.49.369.561 I slot print_timing: id 3 | task 4607 | n_gen = 130, tg = 4.20 t/s, tg_3s = 4.76 t/s 23.50.637.089 I slot print_timing: id 1 | task 3902 | n_gen = 827, tg = 4.12 t/s, tg_3s = 4.75 t/s 23.52.535.711 I slot print_timing: id 2 | task 4623 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.74 t/s 23.52.535.860 I slot print_timing: id 3 | task 4607 | n_gen = 145, tg = 4.25 t/s, tg_3s = 4.74 t/s 23.53.800.934 I slot print_timing: id 1 | task 3902 | n_gen = 842, tg = 4.13 t/s, tg_3s = 4.74 t/s 23.55.699.337 I slot print_timing: id 2 | task 4623 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.74 t/s 23.55.699.484 I slot print_timing: id 3 | task 4607 | n_gen = 160, tg = 4.30 t/s, tg_3s = 4.74 t/s 23.56.120.634 I slot print_timing: id 0 | task 4671 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 23.56.964.667 I slot print_timing: id 1 | task 3902 | n_gen = 857, tg = 4.14 t/s, tg_3s = 4.74 t/s 23.58.862.878 I slot print_timing: id 2 | task 4623 | n_gen = 160, tg = 4.53 t/s, tg_3s = 4.74 t/s 23.58.863.036 I slot print_timing: id 3 | task 4607 | n_gen = 175, tg = 4.33 t/s, tg_3s = 4.74 t/s 23.59.284.440 I slot print_timing: id 0 | task 4671 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 24.00.127.666 I slot print_timing: id 1 | task 3902 | n_gen = 872, tg = 4.15 t/s, tg_3s = 4.74 t/s 24.01.815.530 I slot print_timing: id 3 | task 4607 | prompt eval time = 2450.98 ms / 134 tokens ( 18.29 ms per token, 54.67 tokens per second) 24.01.815.533 I slot print_timing: id 3 | task 4607 | eval time = 43134.56 ms / 189 tokens ( 229.44 ms per token, 4.36 tokens per second) 24.01.815.533 I slot print_timing: id 3 | task 4607 | total time = 45585.54 ms / 323 tokens 24.01.815.534 I slot print_timing: id 3 | task 4607 | graphs reused = 4143 24.01.815.534 I slot print_timing: id 3 | task 4607 | graph reallocs = 0 / 0 (same size) / (changed size) 24.01.815.584 I slot release: id 3 | task 4607 | stop processing: n_tokens = 1447, truncated = 0 24.02.015.151 I slot print_timing: id 2 | task 4623 | n_gen = 175, tg = 4.55 t/s, tg_3s = 4.76 t/s 24.02.015.165 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.792 24.02.015.197 I slot launch_slot_: id 3 | task 4801 | processing task, is_child = 0 24.03.393.967 I slot print_timing: id 0 | task 4671 | n_gen = 129, tg = 4.55 t/s, tg_3s = 3.41 t/s 24.03.394.179 I slot print_timing: id 1 | task 3902 | n_gen = 882, tg = 4.13 t/s, tg_3s = 3.06 t/s 24.05.060.142 I slot print_timing: id 2 | task 4623 | n_gen = 183, tg = 4.41 t/s, tg_3s = 2.63 t/s 24.05.481.767 I slot print_timing: id 0 | task 4671 | prompt eval time = 2069.51 ms / 109 tokens ( 18.99 ms per token, 52.67 tokens per second) 24.05.481.773 I slot print_timing: id 0 | task 4671 | eval time = 30198.54 ms / 138 tokens ( 220.43 ms per token, 4.54 tokens per second) 24.05.481.773 I slot print_timing: id 0 | task 4671 | total time = 32268.06 ms / 247 tokens 24.05.481.774 I slot print_timing: id 0 | task 4671 | graphs reused = 4150 24.05.481.774 I slot print_timing: id 0 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 24.05.481.822 I slot release: id 0 | task 4671 | stop processing: n_tokens = 1371, truncated = 0 24.05.682.301 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.836 24.05.682.355 I slot launch_slot_: id 0 | task 4813 | processing task, is_child = 0 24.07.045.380 I slot print_timing: id 1 | task 3902 | n_gen = 893, tg = 4.11 t/s, tg_3s = 3.01 t/s 24.08.066.023 I slot print_timing: id 2 | task 4623 | n_gen = 191, tg = 4.29 t/s, tg_3s = 2.66 t/s 24.10.174.587 I slot print_timing: id 1 | task 3902 | n_gen = 907, tg = 4.12 t/s, tg_3s = 4.47 t/s 24.11.228.958 I slot print_timing: id 2 | task 4623 | n_gen = 206, tg = 4.32 t/s, tg_3s = 4.74 t/s 24.13.337.112 I slot print_timing: id 1 | task 3902 | n_gen = 922, tg = 4.13 t/s, tg_3s = 4.74 t/s 24.14.391.051 I slot print_timing: id 2 | task 4623 | n_gen = 221, tg = 4.35 t/s, tg_3s = 4.74 t/s 24.16.499.870 I slot print_timing: id 1 | task 3902 | n_gen = 937, tg = 4.13 t/s, tg_3s = 4.74 t/s 24.17.554.546 I slot print_timing: id 2 | task 4623 | n_gen = 236, tg = 4.37 t/s, tg_3s = 4.74 t/s 24.19.664.041 I slot print_timing: id 1 | task 3902 | n_gen = 952, tg = 4.14 t/s, tg_3s = 4.74 t/s 24.20.718.995 I slot print_timing: id 2 | task 4623 | n_gen = 251, tg = 4.39 t/s, tg_3s = 4.74 t/s 24.22.828.826 I slot print_timing: id 1 | task 3902 | n_gen = 967, tg = 4.15 t/s, tg_3s = 4.74 t/s 24.23.883.674 I slot print_timing: id 2 | task 4623 | n_gen = 266, tg = 4.41 t/s, tg_3s = 4.74 t/s 24.25.992.459 I slot print_timing: id 1 | task 3902 | n_gen = 982, tg = 4.16 t/s, tg_3s = 4.74 t/s 24.25.992.756 I slot print_timing: id 3 | task 4801 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 24.27.047.329 I slot print_timing: id 2 | task 4623 | n_gen = 281, tg = 4.42 t/s, tg_3s = 4.74 t/s 24.27.679.876 I slot print_timing: id 0 | task 4813 | prompt eval time = 1748.95 ms / 96 tokens ( 18.22 ms per token, 54.89 tokens per second) 24.27.679.879 I slot print_timing: id 0 | task 4813 | eval time = 20248.55 ms / 97 tokens ( 210.92 ms per token, 4.74 tokens per second) 24.27.679.879 I slot print_timing: id 0 | task 4813 | total time = 21997.51 ms / 193 tokens 24.27.679.880 I slot print_timing: id 0 | task 4813 | graphs reused = 4246 24.27.679.880 I slot print_timing: id 0 | task 4813 | graph reallocs = 0 / 0 (same size) / (changed size) 24.27.679.933 I slot release: id 0 | task 4813 | stop processing: n_tokens = 1317, truncated = 0 24.27.880.173 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.870 24.27.880.208 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 24.29.571.172 I slot print_timing: id 1 | task 3902 | n_gen = 992, tg = 4.14 t/s, tg_3s = 2.79 t/s 24.29.571.494 I slot print_timing: id 3 | task 4801 | n_gen = 110, tg = 4.23 t/s, tg_3s = 2.79 t/s 24.30.172.316 I slot print_timing: id 2 | task 4623 | n_gen = 288, tg = 4.32 t/s, tg_3s = 2.24 t/s 24.32.702.752 I slot print_timing: id 1 | task 3902 | n_gen = 1006, tg = 4.14 t/s, tg_3s = 4.47 t/s 24.32.703.043 I slot print_timing: id 3 | task 4801 | n_gen = 124, tg = 4.25 t/s, tg_3s = 4.47 t/s 24.33.336.023 I slot print_timing: id 2 | task 4623 | n_gen = 303, tg = 4.34 t/s, tg_3s = 4.74 t/s 24.33.547.096 I slot print_timing: id 2 | task 4623 | prompt eval time = 2268.67 ms / 112 tokens ( 20.26 ms per token, 49.37 tokens per second) 24.33.547.102 I slot print_timing: id 2 | task 4623 | eval time = 69785.22 ms / 304 tokens ( 230.31 ms per token, 4.34 tokens per second) 24.33.547.103 I slot print_timing: id 2 | task 4623 | total time = 72053.88 ms / 416 tokens 24.33.547.104 I slot print_timing: id 2 | task 4623 | graphs reused = 4263 24.33.547.104 I slot print_timing: id 2 | task 4623 | graph reallocs = 0 / 0 (same size) / (changed size) 24.33.547.161 I slot release: id 2 | task 4623 | stop processing: n_tokens = 1540, truncated = 0 24.33.833.057 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.744 24.33.833.093 I slot launch_slot_: id 2 | task 4934 | processing task, is_child = 0 24.36.347.986 I slot print_timing: id 1 | task 3902 | n_gen = 1012, tg = 4.11 t/s, tg_3s = 1.65 t/s 24.36.348.166 I slot print_timing: id 3 | task 4801 | n_gen = 130, tg = 3.96 t/s, tg_3s = 1.65 t/s 24.39.155.232 I slot print_timing: id 1 | task 3902 | prompt eval time = 2394.63 ms / 103 tokens ( 23.25 ms per token, 43.01 tokens per second) 24.39.155.237 I slot print_timing: id 1 | task 3902 | eval time = 249071.72 ms / 1024 tokens ( 243.47 ms per token, 4.11 tokens per second) 24.39.155.238 I slot print_timing: id 1 | task 3902 | total time = 251466.35 ms / 1127 tokens 24.39.155.238 I slot print_timing: id 1 | task 3902 | graphs reused = 4273 24.39.155.238 I slot print_timing: id 1 | task 3902 | graph reallocs = 0 / 0 (same size) / (changed size) 24.39.155.285 I slot release: id 1 | task 3902 | stop processing: n_tokens = 2251, truncated = 0 24.39.441.061 I slot print_timing: id 3 | task 4801 | n_gen = 143, tg = 3.98 t/s, tg_3s = 4.20 t/s 24.39.441.065 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.509 24.39.441.101 I slot launch_slot_: id 1 | task 4949 | processing task, is_child = 0 24.42.477.038 I slot print_timing: id 3 | task 4801 | n_gen = 148, tg = 3.80 t/s, tg_3s = 1.65 t/s 24.45.626.413 I slot print_timing: id 3 | task 4801 | n_gen = 163, tg = 3.87 t/s, tg_3s = 4.76 t/s 24.48.774.141 I slot print_timing: id 3 | task 4801 | n_gen = 178, tg = 3.93 t/s, tg_3s = 4.77 t/s 24.51.924.649 I slot print_timing: id 3 | task 4801 | prompt eval time = 1777.33 ms / 95 tokens ( 18.71 ms per token, 53.45 tokens per second) 24.51.924.652 I slot print_timing: id 3 | task 4801 | eval time = 48132.11 ms / 193 tokens ( 250.69 ms per token, 3.99 tokens per second) 24.51.924.653 I slot print_timing: id 3 | task 4801 | total time = 49909.44 ms / 288 tokens 24.51.924.653 I slot print_timing: id 3 | task 4801 | graphs reused = 4320 24.51.924.654 I slot print_timing: id 3 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 24.51.924.700 I slot release: id 3 | task 4801 | stop processing: n_tokens = 1412, truncated = 0 24.52.123.889 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.812 24.52.123.926 I slot launch_slot_: id 3 | task 5001 | processing task, is_child = 0 24.57.156.672 I slot print_timing: id 0 | task 4913 | n_gen = 100, tg = 3.64 t/s, tg_3s = 3.68 t/s 25.00.305.154 I slot print_timing: id 0 | task 4913 | n_gen = 115, tg = 3.76 t/s, tg_3s = 4.76 t/s 25.01.355.819 I slot print_timing: id 2 | task 4934 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 25.03.455.601 I slot print_timing: id 0 | task 4913 | n_gen = 130, tg = 3.85 t/s, tg_3s = 4.76 t/s 25.04.295.756 I slot print_timing: id 1 | task 4949 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 25.04.505.616 I slot print_timing: id 2 | task 4934 | n_gen = 115, tg = 4.12 t/s, tg_3s = 4.76 t/s 25.06.605.887 I slot print_timing: id 0 | task 4913 | n_gen = 145, tg = 3.93 t/s, tg_3s = 4.76 t/s 25.07.445.970 I slot print_timing: id 1 | task 4949 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.76 t/s 25.07.656.247 I slot print_timing: id 2 | task 4934 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.76 t/s 25.09.756.014 I slot print_timing: id 0 | task 4913 | n_gen = 160, tg = 4.00 t/s, tg_3s = 4.76 t/s 25.10.596.284 I slot print_timing: id 1 | task 4949 | n_gen = 130, tg = 4.49 t/s, tg_3s = 4.76 t/s 25.10.806.472 I slot print_timing: id 2 | task 4934 | n_gen = 145, tg = 4.24 t/s, tg_3s = 4.76 t/s 25.12.906.060 I slot print_timing: id 0 | task 4913 | n_gen = 175, tg = 4.05 t/s, tg_3s = 4.76 t/s 25.13.746.626 I slot print_timing: id 1 | task 4949 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.76 t/s 25.13.956.812 I slot print_timing: id 2 | task 4934 | n_gen = 160, tg = 4.28 t/s, tg_3s = 4.76 t/s 25.15.007.786 I slot print_timing: id 3 | task 5001 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 25.16.057.615 I slot print_timing: id 0 | task 4913 | n_gen = 190, tg = 4.10 t/s, tg_3s = 4.76 t/s 25.16.898.317 I slot print_timing: id 1 | task 4949 | n_gen = 160, tg = 4.54 t/s, tg_3s = 4.76 t/s 25.17.108.517 I slot print_timing: id 2 | task 4934 | n_gen = 175, tg = 4.32 t/s, tg_3s = 4.76 t/s 25.18.159.179 I slot print_timing: id 3 | task 5001 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 25.19.209.270 I slot print_timing: id 0 | task 4913 | n_gen = 205, tg = 4.14 t/s, tg_3s = 4.76 t/s 25.20.049.371 I slot print_timing: id 1 | task 4949 | n_gen = 175, tg = 4.55 t/s, tg_3s = 4.76 t/s 25.20.259.770 I slot print_timing: id 2 | task 4934 | n_gen = 190, tg = 4.35 t/s, tg_3s = 4.76 t/s 25.20.680.044 I slot print_timing: id 3 | task 5001 | prompt eval time = 2091.31 ms / 104 tokens ( 20.11 ms per token, 49.73 tokens per second) 25.20.680.049 I slot print_timing: id 3 | task 5001 | eval time = 26464.80 ms / 127 tokens ( 210.04 ms per token, 4.76 tokens per second) 25.20.680.050 I slot print_timing: id 3 | task 5001 | total time = 28556.11 ms / 231 tokens 25.20.680.050 I slot print_timing: id 3 | task 5001 | graphs reused = 4445 25.20.680.051 I slot print_timing: id 3 | task 5001 | graph reallocs = 0 / 0 (same size) / (changed size) 25.20.680.100 I slot release: id 3 | task 5001 | stop processing: n_tokens = 1355, truncated = 0 25.20.879.442 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.846 25.20.879.473 I slot launch_slot_: id 3 | task 5131 | processing task, is_child = 0 25.22.573.217 I slot print_timing: id 0 | task 4913 | n_gen = 214, tg = 4.05 t/s, tg_3s = 2.68 t/s 25.23.181.916 I slot print_timing: id 1 | task 4949 | n_gen = 182, tg = 4.38 t/s, tg_3s = 2.23 t/s 25.23.392.214 I slot print_timing: id 2 | task 4934 | n_gen = 197, tg = 4.21 t/s, tg_3s = 2.23 t/s 25.25.703.616 I slot print_timing: id 0 | task 4913 | n_gen = 228, tg = 4.07 t/s, tg_3s = 4.47 t/s 25.26.334.190 I slot print_timing: id 1 | task 4949 | n_gen = 197, tg = 4.41 t/s, tg_3s = 4.76 t/s 25.26.544.478 I slot print_timing: id 2 | task 4934 | n_gen = 212, tg = 4.24 t/s, tg_3s = 4.76 t/s 25.28.856.040 I slot print_timing: id 0 | task 4913 | n_gen = 243, tg = 4.11 t/s, tg_3s = 4.76 t/s 25.29.486.427 I slot print_timing: id 1 | task 4949 | n_gen = 212, tg = 4.43 t/s, tg_3s = 4.76 t/s 25.29.696.412 I slot print_timing: id 2 | task 4934 | n_gen = 227, tg = 4.28 t/s, tg_3s = 4.76 t/s 25.32.007.371 I slot print_timing: id 0 | task 4913 | n_gen = 258, tg = 4.14 t/s, tg_3s = 4.76 t/s 25.32.638.022 I slot print_timing: id 1 | task 4949 | n_gen = 227, tg = 4.45 t/s, tg_3s = 4.76 t/s 25.32.848.564 I slot print_timing: id 2 | task 4934 | n_gen = 242, tg = 4.30 t/s, tg_3s = 4.76 t/s 25.35.163.244 I slot print_timing: id 0 | task 4913 | n_gen = 273, tg = 4.17 t/s, tg_3s = 4.75 t/s 25.35.793.774 I slot print_timing: id 1 | task 4949 | n_gen = 242, tg = 4.47 t/s, tg_3s = 4.75 t/s 25.36.004.113 I slot print_timing: id 2 | task 4934 | n_gen = 257, tg = 4.33 t/s, tg_3s = 4.75 t/s 25.38.315.735 I slot print_timing: id 0 | task 4913 | n_gen = 288, tg = 4.20 t/s, tg_3s = 4.76 t/s 25.38.946.275 I slot print_timing: id 1 | task 4949 | n_gen = 257, tg = 4.48 t/s, tg_3s = 4.76 t/s 25.39.156.725 I slot print_timing: id 2 | task 4934 | n_gen = 272, tg = 4.35 t/s, tg_3s = 4.76 t/s 25.41.468.194 I slot print_timing: id 0 | task 4913 | n_gen = 303, tg = 4.22 t/s, tg_3s = 4.76 t/s 25.42.099.204 I slot print_timing: id 1 | task 4949 | n_gen = 272, tg = 4.50 t/s, tg_3s = 4.76 t/s 25.42.309.916 I slot print_timing: id 2 | task 4934 | n_gen = 287, tg = 4.37 t/s, tg_3s = 4.76 t/s 25.43.782.154 I slot print_timing: id 3 | task 5131 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.80 t/s 25.44.622.915 I slot print_timing: id 0 | task 4913 | n_gen = 318, tg = 4.25 t/s, tg_3s = 4.75 t/s 25.45.254.110 I slot print_timing: id 1 | task 4949 | n_gen = 287, tg = 4.51 t/s, tg_3s = 4.75 t/s 25.45.464.546 I slot print_timing: id 2 | task 4934 | n_gen = 302, tg = 4.39 t/s, tg_3s = 4.75 t/s 25.46.935.786 I slot print_timing: id 3 | task 5131 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 25.47.776.671 I slot print_timing: id 0 | task 4913 | n_gen = 333, tg = 4.27 t/s, tg_3s = 4.76 t/s 25.48.407.681 I slot print_timing: id 1 | task 4949 | n_gen = 302, tg = 4.52 t/s, tg_3s = 4.76 t/s 25.48.617.923 I slot print_timing: id 2 | task 4934 | n_gen = 317, tg = 4.40 t/s, tg_3s = 4.76 t/s 25.50.090.015 I slot print_timing: id 3 | task 5131 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 25.50.930.290 I slot print_timing: id 0 | task 4913 | n_gen = 348, tg = 4.29 t/s, tg_3s = 4.76 t/s 25.51.561.364 I slot print_timing: id 1 | task 4949 | n_gen = 317, tg = 4.53 t/s, tg_3s = 4.76 t/s 25.51.771.844 I slot print_timing: id 2 | task 4934 | n_gen = 332, tg = 4.42 t/s, tg_3s = 4.76 t/s 25.52.613.802 I slot print_timing: id 3 | task 5131 | prompt eval time = 2090.76 ms / 108 tokens ( 19.36 ms per token, 51.66 tokens per second) 25.52.613.808 I slot print_timing: id 3 | task 5131 | eval time = 29643.56 ms / 142 tokens ( 210.24 ms per token, 4.76 tokens per second) 25.52.613.808 I slot print_timing: id 3 | task 5131 | total time = 31734.32 ms / 250 tokens 25.52.613.809 I slot print_timing: id 3 | task 5131 | graphs reused = 4584 25.52.613.809 I slot print_timing: id 3 | task 5131 | graph reallocs = 0 / 0 (same size) / (changed size) 25.52.613.859 I slot release: id 3 | task 5131 | stop processing: n_tokens = 1374, truncated = 0 25.52.813.416 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.834 25.52.813.452 I slot launch_slot_: id 3 | task 5276 | processing task, is_child = 0 25.54.523.678 I slot print_timing: id 0 | task 4913 | n_gen = 358, tg = 4.22 t/s, tg_3s = 2.78 t/s 25.54.919.623 I slot print_timing: id 1 | task 4949 | n_gen = 325, tg = 4.43 t/s, tg_3s = 2.38 t/s 25.54.919.778 I slot print_timing: id 2 | task 4934 | n_gen = 339, tg = 4.33 t/s, tg_3s = 2.22 t/s 25.55.343.131 I slot print_timing: id 1 | task 4949 | prompt eval time = 2402.88 ms / 117 tokens ( 20.54 ms per token, 48.69 tokens per second) 25.55.343.135 I slot print_timing: id 1 | task 4949 | eval time = 73499.15 ms / 327 tokens ( 225.46 ms per token, 4.44 tokens per second) 25.55.343.136 I slot print_timing: id 1 | task 4949 | total time = 75902.02 ms / 444 tokens 25.55.343.136 I slot print_timing: id 1 | task 4949 | graphs reused = 4585 25.55.343.137 I slot print_timing: id 1 | task 4949 | graph reallocs = 0 / 0 (same size) / (changed size) 25.55.343.180 I slot release: id 1 | task 4949 | stop processing: n_tokens = 1568, truncated = 0 25.55.629.108 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.731 25.55.629.141 I slot launch_slot_: id 1 | task 5282 | processing task, is_child = 0 25.58.029.548 I slot print_timing: id 0 | task 4913 | n_gen = 364, tg = 4.12 t/s, tg_3s = 1.71 t/s 25.58.029.908 I slot print_timing: id 2 | task 4934 | n_gen = 344, tg = 4.22 t/s, tg_3s = 1.61 t/s 26.01.183.810 I slot print_timing: id 0 | task 4913 | n_gen = 379, tg = 4.14 t/s, tg_3s = 4.76 t/s 26.01.184.093 I slot print_timing: id 2 | task 4934 | n_gen = 359, tg = 4.24 t/s, tg_3s = 4.76 t/s 26.04.336.539 I slot print_timing: id 0 | task 4913 | n_gen = 394, tg = 4.16 t/s, tg_3s = 4.76 t/s 26.04.336.805 I slot print_timing: id 2 | task 4934 | n_gen = 374, tg = 4.26 t/s, tg_3s = 4.76 t/s 26.07.489.980 I slot print_timing: id 0 | task 4913 | n_gen = 409, tg = 4.18 t/s, tg_3s = 4.76 t/s 26.07.490.253 I slot print_timing: id 2 | task 4934 | n_gen = 389, tg = 4.28 t/s, tg_3s = 4.76 t/s 26.10.644.407 I slot print_timing: id 0 | task 4913 | n_gen = 424, tg = 4.20 t/s, tg_3s = 4.76 t/s 26.10.644.700 I slot print_timing: id 2 | task 4934 | n_gen = 404, tg = 4.30 t/s, tg_3s = 4.76 t/s 26.13.799.699 I slot print_timing: id 0 | task 4913 | prompt eval time = 2078.33 ms / 122 tokens ( 17.04 ms per token, 58.70 tokens per second) 26.13.799.702 I slot print_timing: id 0 | task 4913 | eval time = 103841.15 ms / 439 tokens ( 237.08 ms per token, 4.22 tokens per second) 26.13.799.702 I slot print_timing: id 0 | task 4913 | total time = 105919.48 ms / 561 tokens 26.13.799.703 I slot print_timing: id 0 | task 4913 | graphs reused = 4659 26.13.799.703 I slot print_timing: id 0 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 26.13.799.753 I slot release: id 0 | task 4913 | stop processing: n_tokens = 1685, truncated = 0 26.13.800.036 I slot print_timing: id 2 | task 4934 | n_gen = 419, tg = 4.31 t/s, tg_3s = 4.75 t/s 26.13.999.571 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.680 26.13.999.607 I slot launch_slot_: id 0 | task 5361 | processing task, is_child = 0 26.16.918.413 I slot print_timing: id 2 | task 4934 | n_gen = 426, tg = 4.25 t/s, tg_3s = 2.24 t/s 26.19.439.114 I slot print_timing: id 3 | task 5276 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 26.20.069.198 I slot print_timing: id 2 | task 4934 | n_gen = 441, tg = 4.26 t/s, tg_3s = 4.76 t/s 26.20.489.510 I slot print_timing: id 1 | task 5282 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 26.22.590.915 I slot print_timing: id 3 | task 5276 | n_gen = 115, tg = 4.12 t/s, tg_3s = 4.76 t/s 26.23.220.969 I slot print_timing: id 2 | task 4934 | n_gen = 456, tg = 4.28 t/s, tg_3s = 4.76 t/s 26.23.641.007 I slot print_timing: id 1 | task 5282 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.76 t/s 26.25.742.445 I slot print_timing: id 3 | task 5276 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.76 t/s 26.26.372.766 I slot print_timing: id 2 | task 4934 | n_gen = 471, tg = 4.29 t/s, tg_3s = 4.76 t/s 26.26.792.411 I slot print_timing: id 1 | task 5282 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.76 t/s 26.27.213.375 I slot print_timing: id 2 | task 4934 | prompt eval time = 3000.07 ms / 166 tokens ( 18.07 ms per token, 55.33 tokens per second) 26.27.213.380 I slot print_timing: id 2 | task 4934 | eval time = 110380.20 ms / 475 tokens ( 232.87 ms per token, 4.29 tokens per second) 26.27.213.380 I slot print_timing: id 2 | task 4934 | total time = 113380.27 ms / 641 tokens 26.27.213.381 I slot print_timing: id 2 | task 4934 | graphs reused = 4712 26.27.213.381 I slot print_timing: id 2 | task 4934 | graph reallocs = 0 / 0 (same size) / (changed size) 26.27.213.426 I slot release: id 2 | task 4934 | stop processing: n_tokens = 1765, truncated = 0 26.27.498.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.649 26.27.498.841 I slot launch_slot_: id 2 | task 5418 | processing task, is_child = 0 26.29.289.598 I slot print_timing: id 3 | task 5276 | n_gen = 139, tg = 4.02 t/s, tg_3s = 2.54 t/s 26.29.984.397 I slot print_timing: id 1 | task 5282 | prompt eval time = 2400.62 ms / 112 tokens ( 21.43 ms per token, 46.65 tokens per second) 26.29.984.402 I slot print_timing: id 1 | task 5282 | eval time = 31954.62 ms / 136 tokens ( 236.70 ms per token, 4.22 tokens per second) 26.29.984.403 I slot print_timing: id 1 | task 5282 | total time = 34355.25 ms / 248 tokens 26.29.984.403 I slot print_timing: id 1 | task 5282 | graphs reused = 4712 26.29.984.404 I slot print_timing: id 1 | task 5282 | graph reallocs = 0 / 0 (same size) / (changed size) 26.29.984.449 I slot release: id 1 | task 5282 | stop processing: n_tokens = 1372, truncated = 0 26.30.269.692 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.835 26.30.269.727 I slot launch_slot_: id 1 | task 5423 | processing task, is_child = 0 26.32.672.303 I slot print_timing: id 3 | task 5276 | n_gen = 144, tg = 3.79 t/s, tg_3s = 1.48 t/s 26.35.822.815 I slot print_timing: id 3 | task 5276 | n_gen = 159, tg = 3.86 t/s, tg_3s = 4.76 t/s 26.38.554.223 I slot print_timing: id 0 | task 5361 | prompt eval time = 2075.40 ms / 116 tokens ( 17.89 ms per token, 55.89 tokens per second) 26.38.554.228 I slot print_timing: id 0 | task 5361 | eval time = 22479.21 ms / 89 tokens ( 255.45 ms per token, 3.91 tokens per second) 26.38.554.229 I slot print_timing: id 0 | task 5361 | total time = 24554.61 ms / 205 tokens 26.38.554.229 I slot print_timing: id 0 | task 5361 | graphs reused = 4739 26.38.554.230 I slot print_timing: id 0 | task 5361 | graph reallocs = 0 / 0 (same size) / (changed size) 26.38.554.275 I slot release: id 0 | task 5361 | stop processing: n_tokens = 1329, truncated = 0 26.38.753.579 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.862 26.38.753.623 I slot launch_slot_: id 0 | task 5455 | processing task, is_child = 0 26.40.429.540 I slot print_timing: id 3 | task 5276 | n_gen = 174, tg = 3.80 t/s, tg_3s = 3.26 t/s 26.43.546.225 I slot print_timing: id 3 | task 5276 | n_gen = 188, tg = 3.85 t/s, tg_3s = 4.49 t/s 26.46.691.899 I slot print_timing: id 3 | task 5276 | n_gen = 203, tg = 3.90 t/s, tg_3s = 4.77 t/s 26.49.842.019 I slot print_timing: id 3 | task 5276 | n_gen = 218, tg = 3.95 t/s, tg_3s = 4.76 t/s 26.52.990.704 I slot print_timing: id 3 | task 5276 | n_gen = 233, tg = 4.00 t/s, tg_3s = 4.76 t/s 26.54.250.678 I slot print_timing: id 2 | task 5418 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.09 t/s 26.55.090.335 I slot print_timing: id 1 | task 5423 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.46 t/s 26.55.510.585 I slot print_timing: id 1 | task 5423 | prompt eval time = 2402.27 ms / 119 tokens ( 20.19 ms per token, 49.54 tokens per second) 26.55.510.587 I slot print_timing: id 1 | task 5423 | eval time = 22838.58 ms / 102 tokens ( 226.12 ms per token, 4.42 tokens per second) 26.55.510.588 I slot print_timing: id 1 | task 5423 | total time = 25240.85 ms / 221 tokens 26.55.510.588 I slot print_timing: id 1 | task 5423 | graphs reused = 4809 26.55.510.589 I slot print_timing: id 1 | task 5423 | graph reallocs = 0 / 0 (same size) / (changed size) 26.55.510.633 I slot release: id 1 | task 5423 | stop processing: n_tokens = 1345, truncated = 0 26.55.796.553 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.852 26.55.796.588 I slot launch_slot_: id 1 | task 5529 | processing task, is_child = 0 26.57.656.031 I slot print_timing: id 2 | task 5418 | n_gen = 108, tg = 3.84 t/s, tg_3s = 2.35 t/s 26.57.656.257 I slot print_timing: id 3 | task 5276 | n_gen = 247, tg = 3.92 t/s, tg_3s = 3.00 t/s 27.00.726.877 I slot print_timing: id 2 | task 5418 | n_gen = 121, tg = 3.88 t/s, tg_3s = 4.23 t/s 27.00.727.048 I slot print_timing: id 3 | task 5276 | n_gen = 260, tg = 3.94 t/s, tg_3s = 4.23 t/s 27.02.406.412 I slot print_timing: id 0 | task 5455 | prompt eval time = 2060.44 ms / 103 tokens ( 20.00 ms per token, 49.99 tokens per second) 27.02.406.416 I slot print_timing: id 0 | task 5455 | eval time = 21592.34 ms / 94 tokens ( 232.18 ms per token, 4.31 tokens per second) 27.02.406.417 I slot print_timing: id 0 | task 5455 | total time = 23652.78 ms / 197 tokens 27.02.406.417 I slot print_timing: id 0 | task 5455 | graphs reused = 4828 27.02.406.418 I slot print_timing: id 0 | task 5455 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.406.465 I slot release: id 0 | task 5455 | stop processing: n_tokens = 1321, truncated = 0 27.02.606.254 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.868 27.02.606.283 I slot launch_slot_: id 0 | task 5553 | processing task, is_child = 0 27.04.285.408 I slot print_timing: id 2 | task 5418 | n_gen = 131, tg = 3.77 t/s, tg_3s = 2.81 t/s 27.04.285.582 I slot print_timing: id 3 | task 5276 | n_gen = 270, tg = 3.88 t/s, tg_3s = 2.81 t/s 27.07.405.590 I slot print_timing: id 2 | task 5418 | n_gen = 145, tg = 3.83 t/s, tg_3s = 4.49 t/s 27.07.405.743 I slot print_timing: id 3 | task 5276 | n_gen = 284, tg = 3.90 t/s, tg_3s = 4.49 t/s 27.10.556.516 I slot print_timing: id 2 | task 5418 | n_gen = 160, tg = 3.90 t/s, tg_3s = 4.76 t/s 27.10.556.671 I slot print_timing: id 3 | task 5276 | n_gen = 299, tg = 3.94 t/s, tg_3s = 4.76 t/s 27.13.705.722 I slot print_timing: id 2 | task 5418 | n_gen = 175, tg = 3.96 t/s, tg_3s = 4.76 t/s 27.13.705.873 I slot print_timing: id 3 | task 5276 | n_gen = 314, tg = 3.97 t/s, tg_3s = 4.76 t/s 27.16.856.964 I slot print_timing: id 2 | task 5418 | n_gen = 190, tg = 4.01 t/s, tg_3s = 4.76 t/s 27.16.857.113 I slot print_timing: id 3 | task 5276 | n_gen = 329, tg = 4.00 t/s, tg_3s = 4.76 t/s 27.20.007.151 I slot print_timing: id 2 | task 5418 | n_gen = 205, tg = 4.06 t/s, tg_3s = 4.76 t/s 27.20.007.306 I slot print_timing: id 3 | task 5276 | n_gen = 344, tg = 4.03 t/s, tg_3s = 4.76 t/s 27.20.637.413 I slot print_timing: id 1 | task 5529 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.46 t/s 27.23.159.233 I slot print_timing: id 2 | task 5418 | n_gen = 220, tg = 4.10 t/s, tg_3s = 4.76 t/s 27.23.159.394 I slot print_timing: id 3 | task 5276 | n_gen = 359, tg = 4.06 t/s, tg_3s = 4.76 t/s 27.23.789.771 I slot print_timing: id 1 | task 5529 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 27.23.789.935 I slot print_timing: id 2 | task 5418 | prompt eval time = 2273.02 ms / 119 tokens ( 19.10 ms per token, 52.35 tokens per second) 27.23.789.937 I slot print_timing: id 2 | task 5418 | eval time = 54018.07 ms / 223 tokens ( 243.32 ms per token, 4.11 tokens per second) 27.23.789.937 I slot print_timing: id 2 | task 5418 | total time = 56291.09 ms / 342 tokens 27.23.789.938 I slot print_timing: id 2 | task 5418 | graphs reused = 4918 27.23.789.938 I slot print_timing: id 2 | task 5418 | graph reallocs = 0 / 0 (same size) / (changed size) 27.23.789.983 I slot release: id 2 | task 5418 | stop processing: n_tokens = 1466, truncated = 0 27.24.073.992 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.782 27.24.074.036 I slot launch_slot_: id 2 | task 5648 | processing task, is_child = 0 27.26.232.137 I slot print_timing: id 3 | task 5276 | n_gen = 366, tg = 4.00 t/s, tg_3s = 2.28 t/s 27.26.862.262 I slot print_timing: id 1 | task 5529 | n_gen = 122, tg = 4.22 t/s, tg_3s = 2.28 t/s 27.27.072.153 I slot print_timing: id 0 | task 5553 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.46 t/s 27.29.383.064 I slot print_timing: id 3 | task 5276 | n_gen = 381, tg = 4.02 t/s, tg_3s = 4.76 t/s 27.30.013.113 I slot print_timing: id 1 | task 5529 | n_gen = 137, tg = 4.28 t/s, tg_3s = 4.76 t/s 27.30.223.155 I slot print_timing: id 0 | task 5553 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 27.32.113.112 I slot print_timing: id 0 | task 5553 | prompt eval time = 2064.71 ms / 108 tokens ( 19.12 ms per token, 52.31 tokens per second) 27.32.113.117 I slot print_timing: id 0 | task 5553 | eval time = 27442.11 ms / 124 tokens ( 223.11 ms per token, 4.48 tokens per second) 27.32.113.118 I slot print_timing: id 0 | task 5553 | total time = 29506.82 ms / 232 tokens 27.32.113.118 I slot print_timing: id 0 | task 5553 | graphs reused = 4946 27.32.113.118 I slot print_timing: id 0 | task 5553 | graph reallocs = 0 / 0 (same size) / (changed size) 27.32.113.160 I slot release: id 0 | task 5553 | stop processing: n_tokens = 1356, truncated = 0 27.32.312.870 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.845 27.32.312.899 I slot launch_slot_: id 0 | task 5681 | processing task, is_child = 0 27.33.664.784 I slot print_timing: id 1 | task 5529 | n_gen = 149, tg = 4.17 t/s, tg_3s = 3.29 t/s 27.33.665.162 I slot print_timing: id 3 | task 5276 | n_gen = 396, tg = 4.00 t/s, tg_3s = 3.50 t/s 27.36.785.291 I slot print_timing: id 1 | task 5529 | n_gen = 163, tg = 4.20 t/s, tg_3s = 4.49 t/s 27.36.785.578 I slot print_timing: id 3 | task 5276 | n_gen = 410, tg = 4.02 t/s, tg_3s = 4.49 t/s 27.39.935.654 I slot print_timing: id 1 | task 5529 | n_gen = 178, tg = 4.24 t/s, tg_3s = 4.76 t/s 27.39.935.942 I slot print_timing: id 3 | task 5276 | n_gen = 425, tg = 4.04 t/s, tg_3s = 4.76 t/s 27.40.566.250 I slot print_timing: id 1 | task 5529 | prompt eval time = 2407.79 ms / 120 tokens ( 20.06 ms per token, 49.84 tokens per second) 27.40.566.252 I slot print_timing: id 1 | task 5529 | eval time = 42361.86 ms / 181 tokens ( 235.34 ms per token, 4.25 tokens per second) 27.40.566.253 I slot print_timing: id 1 | task 5529 | total time = 44769.65 ms / 301 tokens 27.40.566.253 I slot print_timing: id 1 | task 5529 | graphs reused = 4977 27.40.566.254 I slot print_timing: id 1 | task 5529 | graph reallocs = 0 / 0 (same size) / (changed size) 27.40.566.298 I slot release: id 1 | task 5529 | stop processing: n_tokens = 1425, truncated = 0 27.40.851.753 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.805 27.40.851.801 I slot launch_slot_: id 1 | task 5716 | processing task, is_child = 0 27.43.416.521 I slot print_timing: id 3 | task 5276 | n_gen = 430, tg = 3.95 t/s, tg_3s = 1.44 t/s 27.44.388.121 I slot print_timing: id 2 | task 5648 | prompt eval time = 1945.17 ms / 97 tokens ( 20.05 ms per token, 49.87 tokens per second) 27.44.388.126 I slot print_timing: id 2 | task 5648 | eval time = 18368.91 ms / 69 tokens ( 270.13 ms per token, 3.70 tokens per second) 27.44.388.127 I slot print_timing: id 2 | task 5648 | total time = 20314.08 ms / 166 tokens 27.44.388.127 I slot print_timing: id 2 | task 5648 | graphs reused = 4978 27.44.388.128 I slot print_timing: id 2 | task 5648 | graph reallocs = 0 / 0 (same size) / (changed size) 27.44.388.174 I slot release: id 2 | task 5648 | stop processing: n_tokens = 1290, truncated = 0 27.44.673.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.888 27.44.673.446 I slot launch_slot_: id 2 | task 5722 | processing task, is_child = 0 27.46.466.059 I slot print_timing: id 3 | task 5276 | n_gen = 435, tg = 3.89 t/s, tg_3s = 1.64 t/s 27.49.262.252 I slot print_timing: id 3 | task 5276 | prompt eval time = 2106.54 ms / 133 tokens ( 15.84 ms per token, 63.14 tokens per second) 27.49.262.255 I slot print_timing: id 3 | task 5276 | eval time = 114342.26 ms / 447 tokens ( 256.37 ms per token, 3.90 tokens per second) 27.49.262.256 I slot print_timing: id 3 | task 5276 | total time = 116448.79 ms / 580 tokens 27.49.262.257 I slot print_timing: id 3 | task 5276 | graphs reused = 4988 27.49.262.257 I slot print_timing: id 3 | task 5276 | graph reallocs = 0 / 0 (same size) / (changed size) 27.49.262.312 I slot release: id 3 | task 5276 | stop processing: n_tokens = 1704, truncated = 0 27.49.461.288 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.673 27.49.461.319 I slot launch_slot_: id 3 | task 5737 | processing task, is_child = 0 27.56.386.196 I slot print_timing: id 0 | task 5681 | prompt eval time = 1739.16 ms / 100 tokens ( 17.39 ms per token, 57.50 tokens per second) 27.56.386.200 I slot print_timing: id 0 | task 5681 | eval time = 22334.13 ms / 77 tokens ( 293.87 ms per token, 3.40 tokens per second) 27.56.386.201 I slot print_timing: id 0 | task 5681 | total time = 24073.29 ms / 177 tokens 27.56.386.202 I slot print_timing: id 0 | task 5681 | graphs reused = 5010 27.56.386.202 I slot print_timing: id 0 | task 5681 | graph reallocs = 0 / 0 (same size) / (changed size) 27.56.386.243 I slot release: id 0 | task 5681 | stop processing: n_tokens = 1301, truncated = 0 27.56.585.708 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.881 27.56.585.741 I slot launch_slot_: id 0 | task 5764 | processing task, is_child = 0 28.09.985.661 I slot print_timing: id 1 | task 5716 | n_gen = 100, tg = 3.80 t/s, tg_3s = 3.84 t/s 28.11.035.929 I slot print_timing: id 2 | task 5722 | n_gen = 100, tg = 4.11 t/s, tg_3s = 4.15 t/s 28.13.135.666 I slot print_timing: id 1 | task 5716 | n_gen = 115, tg = 3.91 t/s, tg_3s = 4.76 t/s 28.13.975.186 I slot print_timing: id 3 | task 5737 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.46 t/s 28.14.185.011 I slot print_timing: id 2 | task 5722 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.76 t/s 28.16.284.528 I slot print_timing: id 1 | task 5716 | n_gen = 130, tg = 3.99 t/s, tg_3s = 4.76 t/s 28.17.124.583 I slot print_timing: id 3 | task 5737 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 28.17.334.424 I slot print_timing: id 2 | task 5722 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.76 t/s 28.19.434.263 I slot print_timing: id 0 | task 5764 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 28.19.434.410 I slot print_timing: id 1 | task 5716 | n_gen = 145, tg = 4.06 t/s, tg_3s = 4.76 t/s 28.20.274.395 I slot print_timing: id 3 | task 5737 | n_gen = 130, tg = 4.49 t/s, tg_3s = 4.76 t/s 28.20.484.532 I slot print_timing: id 2 | task 5722 | n_gen = 145, tg = 4.29 t/s, tg_3s = 4.76 t/s 28.22.584.852 I slot print_timing: id 0 | task 5764 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 28.22.584.998 I slot print_timing: id 1 | task 5716 | n_gen = 160, tg = 4.12 t/s, tg_3s = 4.76 t/s 28.23.425.619 I slot print_timing: id 3 | task 5737 | n_gen = 145, tg = 4.52 t/s, tg_3s = 4.76 t/s 28.23.635.720 I slot print_timing: id 2 | task 5722 | n_gen = 160, tg = 4.33 t/s, tg_3s = 4.76 t/s 28.23.845.884 I slot print_timing: id 3 | task 5737 | prompt eval time = 2096.71 ms / 114 tokens ( 18.39 ms per token, 54.37 tokens per second) 28.23.845.889 I slot print_timing: id 3 | task 5737 | eval time = 32287.85 ms / 147 tokens ( 221.15 ms per token, 4.52 tokens per second) 28.23.845.890 I slot print_timing: id 3 | task 5737 | total time = 34384.56 ms / 261 tokens 28.23.845.890 I slot print_timing: id 3 | task 5737 | graphs reused = 5130 28.23.845.891 I slot print_timing: id 3 | task 5737 | graph reallocs = 0 / 0 (same size) / (changed size) 28.23.845.939 I slot release: id 3 | task 5737 | stop processing: n_tokens = 1385, truncated = 0 28.24.044.188 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.827 28.24.044.230 I slot launch_slot_: id 3 | task 5888 | processing task, is_child = 0 28.25.747.712 I slot print_timing: id 0 | task 5764 | n_gen = 123, tg = 4.50 t/s, tg_3s = 2.53 t/s 28.25.747.933 I slot print_timing: id 1 | task 5716 | n_gen = 168, tg = 4.00 t/s, tg_3s = 2.53 t/s 28.26.776.840 I slot print_timing: id 2 | task 5722 | n_gen = 167, tg = 4.17 t/s, tg_3s = 2.23 t/s 28.28.877.071 I slot print_timing: id 0 | task 5764 | n_gen = 137, tg = 4.50 t/s, tg_3s = 4.47 t/s 28.28.877.211 I slot print_timing: id 1 | task 5716 | n_gen = 182, tg = 4.03 t/s, tg_3s = 4.47 t/s 28.29.926.894 I slot print_timing: id 2 | task 5722 | n_gen = 182, tg = 4.21 t/s, tg_3s = 4.76 t/s 28.31.397.122 I slot print_timing: id 2 | task 5722 | prompt eval time = 2276.21 ms / 119 tokens ( 19.13 ms per token, 52.28 tokens per second) 28.31.397.127 I slot print_timing: id 2 | task 5722 | eval time = 44447.45 ms / 189 tokens ( 236.42 ms per token, 4.23 tokens per second) 28.31.397.127 I slot print_timing: id 2 | task 5722 | total time = 46723.67 ms / 308 tokens 28.31.397.128 I slot print_timing: id 2 | task 5722 | graphs reused = 5154 28.31.397.128 I slot print_timing: id 2 | task 5722 | graph reallocs = 0 / 0 (same size) / (changed size) 28.31.397.177 I slot release: id 2 | task 5722 | stop processing: n_tokens = 1432, truncated = 0 28.31.682.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.800 28.31.682.428 I slot launch_slot_: id 2 | task 5917 | processing task, is_child = 0 28.33.135.030 I slot print_timing: id 0 | task 5764 | n_gen = 151, tg = 4.35 t/s, tg_3s = 3.29 t/s 28.33.135.239 I slot print_timing: id 1 | task 5716 | n_gen = 196, tg = 3.97 t/s, tg_3s = 3.29 t/s 28.36.137.628 I slot print_timing: id 0 | task 5764 | n_gen = 164, tg = 4.35 t/s, tg_3s = 4.33 t/s 28.36.137.779 I slot print_timing: id 1 | task 5716 | n_gen = 209, tg = 3.99 t/s, tg_3s = 4.33 t/s 28.39.287.337 I slot print_timing: id 0 | task 5764 | n_gen = 179, tg = 4.38 t/s, tg_3s = 4.76 t/s 28.39.287.488 I slot print_timing: id 1 | task 5716 | n_gen = 224, tg = 4.03 t/s, tg_3s = 4.76 t/s 28.42.438.063 I slot print_timing: id 0 | task 5764 | n_gen = 194, tg = 4.41 t/s, tg_3s = 4.76 t/s 28.42.438.201 I slot print_timing: id 1 | task 5716 | n_gen = 239, tg = 4.07 t/s, tg_3s = 4.76 t/s 28.43.490.526 I slot print_timing: id 0 | task 5764 | prompt eval time = 2062.05 ms / 104 tokens ( 19.83 ms per token, 50.44 tokens per second) 28.43.490.532 I slot print_timing: id 0 | task 5764 | eval time = 44842.74 ms / 199 tokens ( 226.48 ms per token, 4.42 tokens per second) 28.43.490.533 I slot print_timing: id 0 | task 5764 | total time = 46904.78 ms / 303 tokens 28.43.490.533 I slot print_timing: id 0 | task 5764 | graphs reused = 5199 28.43.490.534 I slot print_timing: id 0 | task 5764 | graph reallocs = 0 / 0 (same size) / (changed size) 28.43.490.577 I slot release: id 0 | task 5764 | stop processing: n_tokens = 1427, truncated = 0 28.43.690.582 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.803 28.43.690.613 I slot launch_slot_: id 0 | task 5968 | processing task, is_child = 0 28.45.777.750 I slot print_timing: id 1 | task 5716 | n_gen = 247, tg = 3.98 t/s, tg_3s = 2.40 t/s 28.48.929.272 I slot print_timing: id 1 | task 5716 | n_gen = 262, tg = 4.02 t/s, tg_3s = 4.76 t/s 28.50.188.035 I slot print_timing: id 3 | task 5888 | n_gen = 100, tg = 4.12 t/s, tg_3s = 4.16 t/s 28.52.076.825 I slot print_timing: id 1 | task 5716 | n_gen = 277, tg = 4.05 t/s, tg_3s = 4.77 t/s 28.52.077.119 I slot print_timing: id 3 | task 5888 | prompt eval time = 2100.32 ms / 117 tokens ( 17.95 ms per token, 55.71 tokens per second) 28.52.077.123 I slot print_timing: id 3 | task 5888 | eval time = 25932.56 ms / 109 tokens ( 240.12 ms per token, 4.16 tokens per second) 28.52.077.125 I slot print_timing: id 3 | task 5888 | total time = 28032.88 ms / 226 tokens 28.52.077.125 I slot print_timing: id 3 | task 5888 | graphs reused = 5229 28.52.077.125 I slot print_timing: id 3 | task 5888 | graph reallocs = 0 / 0 (same size) / (changed size) 28.52.077.173 I slot release: id 3 | task 5888 | stop processing: n_tokens = 1350, truncated = 0 28.52.276.487 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.849 28.52.276.521 I slot launch_slot_: id 3 | task 6002 | processing task, is_child = 0 28.55.091.400 I slot print_timing: id 1 | task 5716 | n_gen = 285, tg = 3.99 t/s, tg_3s = 2.65 t/s 28.56.560.113 I slot print_timing: id 2 | task 5917 | prompt eval time = 1936.79 ms / 88 tokens ( 22.01 ms per token, 45.44 tokens per second) 28.56.560.119 I slot print_timing: id 2 | task 5917 | eval time = 22940.89 ms / 96 tokens ( 241.48 ms per token, 4.14 tokens per second) 28.56.560.119 I slot print_timing: id 2 | task 5917 | total time = 24877.68 ms / 184 tokens 28.56.560.120 I slot print_timing: id 2 | task 5917 | graphs reused = 5240 28.56.560.120 I slot print_timing: id 2 | task 5917 | graph reallocs = 0 / 0 (same size) / (changed size) 28.56.560.162 I slot release: id 2 | task 5917 | stop processing: n_tokens = 1308, truncated = 0 28.56.845.771 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.876 28.56.845.820 I slot launch_slot_: id 2 | task 6018 | processing task, is_child = 0 28.58.997.728 I slot print_timing: id 1 | task 5716 | n_gen = 294, tg = 3.90 t/s, tg_3s = 2.30 t/s 29.02.002.251 I slot print_timing: id 1 | task 5716 | n_gen = 307, tg = 3.92 t/s, tg_3s = 4.33 t/s 29.05.151.249 I slot print_timing: id 1 | task 5716 | n_gen = 322, tg = 3.95 t/s, tg_3s = 4.76 t/s 29.08.299.871 I slot print_timing: id 1 | task 5716 | n_gen = 337, tg = 3.98 t/s, tg_3s = 4.76 t/s 29.10.189.381 I slot print_timing: id 0 | task 5968 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.10 t/s 29.11.449.770 I slot print_timing: id 1 | task 5716 | n_gen = 352, tg = 4.01 t/s, tg_3s = 4.76 t/s 29.13.340.380 I slot print_timing: id 0 | task 5968 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.76 t/s 29.14.601.174 I slot print_timing: id 1 | task 5716 | n_gen = 367, tg = 4.04 t/s, tg_3s = 4.76 t/s 29.15.441.637 I slot print_timing: id 3 | task 6002 | prompt eval time = 1762.75 ms / 87 tokens ( 20.26 ms per token, 49.35 tokens per second) 29.15.441.642 I slot print_timing: id 3 | task 6002 | eval time = 21402.36 ms / 92 tokens ( 235.19 ms per token, 4.25 tokens per second) 29.15.441.643 I slot print_timing: id 3 | task 6002 | total time = 23165.11 ms / 179 tokens 29.15.441.643 I slot print_timing: id 3 | task 6002 | graphs reused = 5315 29.15.441.644 I slot print_timing: id 3 | task 6002 | graph reallocs = 0 / 0 (same size) / (changed size) 29.15.441.689 I slot release: id 3 | task 6002 | stop processing: n_tokens = 1303, truncated = 0 29.15.640.635 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.880 29.15.640.670 I slot launch_slot_: id 3 | task 6098 | processing task, is_child = 0 29.17.344.834 I slot print_timing: id 0 | task 5968 | n_gen = 127, tg = 3.99 t/s, tg_3s = 3.00 t/s 29.17.742.931 I slot print_timing: id 1 | task 5716 | n_gen = 374, tg = 3.98 t/s, tg_3s = 2.23 t/s 29.20.475.921 I slot print_timing: id 0 | task 5968 | n_gen = 141, tg = 4.03 t/s, tg_3s = 4.47 t/s 29.20.896.412 I slot print_timing: id 1 | task 5716 | n_gen = 389, tg = 4.00 t/s, tg_3s = 4.76 t/s 29.21.736.640 I slot print_timing: id 1 | task 5716 | prompt eval time = 3113.34 ms / 172 tokens ( 18.10 ms per token, 55.25 tokens per second) 29.21.736.645 I slot print_timing: id 1 | task 5716 | eval time = 97771.49 ms / 393 tokens ( 249.42 ms per token, 4.01 tokens per second) 29.21.736.645 I slot print_timing: id 1 | task 5716 | total time = 100884.83 ms / 565 tokens 29.21.736.646 I slot print_timing: id 1 | task 5716 | graphs reused = 5333 29.21.736.646 I slot print_timing: id 1 | task 5716 | graph reallocs = 0 / 0 (same size) / (changed size) 29.21.736.692 I slot release: id 1 | task 5716 | stop processing: n_tokens = 1689, truncated = 0 29.22.021.905 I slot print_timing: id 2 | task 6018 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.44 t/s 29.22.022.066 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.679 29.22.022.108 I slot launch_slot_: id 1 | task 6121 | processing task, is_child = 0 29.23.869.585 I slot print_timing: id 0 | task 5968 | n_gen = 149, tg = 3.89 t/s, tg_3s = 2.36 t/s 29.25.048.420 I slot print_timing: id 2 | task 6018 | n_gen = 105, tg = 4.07 t/s, tg_3s = 1.65 t/s 29.26.937.943 I slot print_timing: id 0 | task 5968 | n_gen = 162, tg = 3.91 t/s, tg_3s = 4.24 t/s 29.28.197.150 I slot print_timing: id 2 | task 6018 | n_gen = 120, tg = 4.14 t/s, tg_3s = 4.76 t/s 29.30.086.781 I slot print_timing: id 0 | task 5968 | n_gen = 177, tg = 3.97 t/s, tg_3s = 4.76 t/s 29.31.347.212 I slot print_timing: id 2 | task 6018 | n_gen = 135, tg = 4.21 t/s, tg_3s = 4.76 t/s 29.33.237.306 I slot print_timing: id 0 | task 5968 | n_gen = 192, tg = 4.02 t/s, tg_3s = 4.76 t/s 29.34.498.071 I slot print_timing: id 2 | task 6018 | n_gen = 150, tg = 4.26 t/s, tg_3s = 4.76 t/s 29.36.388.293 I slot print_timing: id 0 | task 5968 | n_gen = 207, tg = 4.07 t/s, tg_3s = 4.76 t/s 29.37.647.866 I slot print_timing: id 2 | task 6018 | n_gen = 165, tg = 4.30 t/s, tg_3s = 4.76 t/s 29.39.537.458 I slot print_timing: id 0 | task 5968 | n_gen = 222, tg = 4.11 t/s, tg_3s = 4.76 t/s 29.40.587.738 I slot print_timing: id 3 | task 6098 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.38 t/s 29.40.797.868 I slot print_timing: id 2 | task 6018 | n_gen = 180, tg = 4.33 t/s, tg_3s = 4.76 t/s 29.42.688.226 I slot print_timing: id 0 | task 5968 | n_gen = 237, tg = 4.15 t/s, tg_3s = 4.76 t/s 29.43.738.875 I slot print_timing: id 3 | task 6098 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.76 t/s 29.43.948.789 I slot print_timing: id 2 | task 6018 | n_gen = 195, tg = 4.36 t/s, tg_3s = 4.76 t/s 29.45.209.566 I slot print_timing: id 1 | task 6121 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 29.45.629.804 I slot print_timing: id 0 | task 5968 | prompt eval time = 2087.00 ms / 129 tokens ( 16.18 ms per token, 61.81 tokens per second) 29.45.629.809 I slot print_timing: id 0 | task 5968 | eval time = 59852.19 ms / 251 tokens ( 239.41 ms per token, 4.18 tokens per second) 29.45.629.810 I slot print_timing: id 0 | task 5968 | total time = 61939.18 ms / 380 tokens 29.45.629.810 I slot print_timing: id 0 | task 5968 | graphs reused = 5433 29.45.629.810 I slot print_timing: id 0 | task 5968 | graph reallocs = 0 / 0 (same size) / (changed size) 29.45.629.864 I slot release: id 0 | task 5968 | stop processing: n_tokens = 1504, truncated = 0 29.45.829.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.762 29.45.829.558 I slot launch_slot_: id 0 | task 6226 | processing task, is_child = 0 29.47.866.806 I slot print_timing: id 2 | task 6018 | n_gen = 205, tg = 4.22 t/s, tg_3s = 2.55 t/s 29.47.867.010 I slot print_timing: id 3 | task 6098 | n_gen = 126, tg = 4.15 t/s, tg_3s = 2.66 t/s 29.48.253.623 I slot print_timing: id 1 | task 6121 | n_gen = 105, tg = 4.36 t/s, tg_3s = 1.64 t/s 29.50.986.143 I slot print_timing: id 2 | task 6018 | n_gen = 219, tg = 4.23 t/s, tg_3s = 4.49 t/s 29.50.986.301 I slot print_timing: id 3 | task 6098 | n_gen = 140, tg = 4.18 t/s, tg_3s = 4.49 t/s 29.51.405.603 I slot print_timing: id 1 | task 6121 | n_gen = 120, tg = 4.41 t/s, tg_3s = 4.76 t/s 29.54.135.853 I slot print_timing: id 2 | task 6018 | n_gen = 234, tg = 4.26 t/s, tg_3s = 4.76 t/s 29.54.136.011 I slot print_timing: id 3 | task 6098 | n_gen = 155, tg = 4.23 t/s, tg_3s = 4.76 t/s 29.54.556.174 I slot print_timing: id 1 | task 6121 | n_gen = 135, tg = 4.45 t/s, tg_3s = 4.76 t/s 29.57.285.256 I slot print_timing: id 2 | task 6018 | n_gen = 249, tg = 4.29 t/s, tg_3s = 4.76 t/s 29.57.285.408 I slot print_timing: id 3 | task 6098 | n_gen = 170, tg = 4.27 t/s, tg_3s = 4.76 t/s 29.57.705.271 I slot print_timing: id 1 | task 6121 | n_gen = 150, tg = 4.48 t/s, tg_3s = 4.76 t/s 30.00.439.383 I slot print_timing: id 2 | task 6018 | n_gen = 264, tg = 4.31 t/s, tg_3s = 4.76 t/s 30.00.439.531 I slot print_timing: id 3 | task 6098 | n_gen = 185, tg = 4.31 t/s, tg_3s = 4.76 t/s 30.00.859.396 I slot print_timing: id 1 | task 6121 | n_gen = 165, tg = 4.50 t/s, tg_3s = 4.76 t/s 30.02.119.576 I slot print_timing: id 3 | task 6098 | prompt eval time = 2102.61 ms / 118 tokens ( 17.82 ms per token, 56.12 tokens per second) 30.02.119.582 I slot print_timing: id 3 | task 6098 | eval time = 44376.29 ms / 193 tokens ( 231.13 ms per token, 4.33 tokens per second) 30.02.119.583 I slot print_timing: id 3 | task 6098 | total time = 46478.90 ms / 311 tokens 30.02.119.583 I slot print_timing: id 3 | task 6098 | graphs reused = 5498 30.02.119.584 I slot print_timing: id 3 | task 6098 | graph reallocs = 0 / 0 (same size) / (changed size) 30.02.119.633 I slot release: id 3 | task 6098 | stop processing: n_tokens = 1435, truncated = 0 30.02.319.319 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.799 30.02.319.350 I slot launch_slot_: id 3 | task 6296 | processing task, is_child = 0 30.03.689.026 I slot print_timing: id 2 | task 6018 | n_gen = 274, tg = 4.25 t/s, tg_3s = 3.08 t/s 30.04.086.206 I slot print_timing: id 1 | task 6121 | n_gen = 174, tg = 4.36 t/s, tg_3s = 2.79 t/s 30.06.818.231 I slot print_timing: id 2 | task 6018 | n_gen = 288, tg = 4.26 t/s, tg_3s = 4.47 t/s 30.07.237.799 I slot print_timing: id 1 | task 6121 | n_gen = 189, tg = 4.39 t/s, tg_3s = 4.76 t/s 30.08.497.520 I slot print_timing: id 2 | task 6018 | prompt eval time = 2635.25 ms / 152 tokens ( 17.34 ms per token, 57.68 tokens per second) 30.08.497.526 I slot print_timing: id 2 | task 6018 | eval time = 69016.43 ms / 296 tokens ( 233.95 ms per token, 4.27 tokens per second) 30.08.497.527 I slot print_timing: id 2 | task 6018 | total time = 71651.69 ms / 448 tokens 30.08.497.527 I slot print_timing: id 2 | task 6018 | graphs reused = 5518 30.08.497.528 I slot print_timing: id 2 | task 6018 | graph reallocs = 0 / 0 (same size) / (changed size) 30.08.497.571 I slot release: id 2 | task 6018 | stop processing: n_tokens = 1572, truncated = 0 30.08.782.419 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.729 30.08.782.453 I slot launch_slot_: id 2 | task 6321 | processing task, is_child = 0 30.10.575.230 I slot print_timing: id 1 | task 6121 | n_gen = 197, tg = 4.25 t/s, tg_3s = 2.40 t/s 30.12.319.194 I slot print_timing: id 0 | task 6226 | n_gen = 100, tg = 4.11 t/s, tg_3s = 4.16 t/s 30.13.579.362 I slot print_timing: id 1 | task 6121 | n_gen = 210, tg = 4.25 t/s, tg_3s = 4.33 t/s 30.15.468.034 I slot print_timing: id 0 | task 6226 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.76 t/s 30.16.728.309 I slot print_timing: id 1 | task 6121 | n_gen = 225, tg = 4.28 t/s, tg_3s = 4.76 t/s 30.18.618.276 I slot print_timing: id 0 | task 6226 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.76 t/s 30.19.878.236 I slot print_timing: id 1 | task 6121 | n_gen = 240, tg = 4.31 t/s, tg_3s = 4.76 t/s 30.21.768.008 I slot print_timing: id 0 | task 6226 | n_gen = 145, tg = 4.30 t/s, tg_3s = 4.76 t/s 30.21.978.254 I slot print_timing: id 3 | task 6296 | prompt eval time = 1767.22 ms / 92 tokens ( 19.21 ms per token, 52.06 tokens per second) 30.21.978.260 I slot print_timing: id 3 | task 6296 | eval time = 17891.68 ms / 77 tokens ( 235.42 ms per token, 4.25 tokens per second) 30.21.978.261 I slot print_timing: id 3 | task 6296 | total time = 19658.90 ms / 169 tokens 30.21.978.262 I slot print_timing: id 3 | task 6296 | graphs reused = 5569 30.21.978.262 I slot print_timing: id 3 | task 6296 | graph reallocs = 0 / 0 (same size) / (changed size) 30.21.978.307 I slot release: id 3 | task 6296 | stop processing: n_tokens = 1293, truncated = 0 30.22.177.509 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.886 30.22.177.539 I slot launch_slot_: id 3 | task 6377 | processing task, is_child = 0 30.23.896.154 I slot print_timing: id 1 | task 6121 | n_gen = 252, tg = 4.22 t/s, tg_3s = 2.99 t/s 30.24.924.746 I slot print_timing: id 0 | task 6226 | n_gen = 152, tg = 4.12 t/s, tg_3s = 2.22 t/s 30.27.024.221 I slot print_timing: id 1 | task 6121 | n_gen = 266, tg = 4.23 t/s, tg_3s = 4.48 t/s 30.28.074.319 I slot print_timing: id 0 | task 6226 | n_gen = 167, tg = 4.17 t/s, tg_3s = 4.76 t/s 30.30.174.727 I slot print_timing: id 1 | task 6121 | n_gen = 281, tg = 4.26 t/s, tg_3s = 4.76 t/s 30.31.224.735 I slot print_timing: id 0 | task 6226 | n_gen = 182, tg = 4.21 t/s, tg_3s = 4.76 t/s 30.33.327.147 I slot print_timing: id 1 | task 6121 | n_gen = 296, tg = 4.28 t/s, tg_3s = 4.76 t/s 30.33.537.498 I slot print_timing: id 2 | task 6321 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 30.34.378.119 I slot print_timing: id 0 | task 6226 | n_gen = 197, tg = 4.25 t/s, tg_3s = 4.76 t/s 30.36.482.495 I slot print_timing: id 1 | task 6121 | n_gen = 311, tg = 4.30 t/s, tg_3s = 4.75 t/s 30.36.692.768 I slot print_timing: id 2 | task 6321 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 30.37.532.909 I slot print_timing: id 0 | task 6226 | n_gen = 212, tg = 4.28 t/s, tg_3s = 4.75 t/s 30.39.634.528 I slot print_timing: id 0 | task 6226 | prompt eval time = 2423.91 ms / 135 tokens ( 17.95 ms per token, 55.70 tokens per second) 30.39.634.531 I slot print_timing: id 0 | task 6226 | eval time = 51381.05 ms / 222 tokens ( 232.49 ms per token, 4.30 tokens per second) 30.39.634.532 I slot print_timing: id 0 | task 6226 | total time = 53804.96 ms / 357 tokens 30.39.634.532 I slot print_timing: id 0 | task 6226 | graphs reused = 5640 30.39.634.532 I slot print_timing: id 0 | task 6226 | graph reallocs = 0 / 0 (same size) / (changed size) 30.39.634.575 I slot release: id 0 | task 6226 | stop processing: n_tokens = 1481, truncated = 0 30.39.634.720 I slot print_timing: id 1 | task 6121 | n_gen = 326, tg = 4.32 t/s, tg_3s = 4.76 t/s 30.39.834.489 I slot print_timing: id 2 | task 6321 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.77 t/s 30.39.834.643 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.774 30.39.834.672 I slot launch_slot_: id 0 | task 6454 | processing task, is_child = 0 30.42.842.407 I slot print_timing: id 1 | task 6121 | n_gen = 335, tg = 4.26 t/s, tg_3s = 2.81 t/s 30.42.842.550 I slot print_timing: id 2 | task 6321 | n_gen = 138, tg = 4.31 t/s, tg_3s = 2.66 t/s 30.45.993.746 I slot print_timing: id 1 | task 6121 | n_gen = 350, tg = 4.28 t/s, tg_3s = 4.76 t/s 30.45.993.908 I slot print_timing: id 2 | task 6321 | n_gen = 153, tg = 4.35 t/s, tg_3s = 4.76 t/s 30.46.414.109 I slot print_timing: id 3 | task 6377 | n_gen = 100, tg = 4.48 t/s, tg_3s = 4.52 t/s 30.49.144.391 I slot print_timing: id 1 | task 6121 | n_gen = 365, tg = 4.30 t/s, tg_3s = 4.76 t/s 30.49.144.541 I slot print_timing: id 2 | task 6321 | n_gen = 168, tg = 4.38 t/s, tg_3s = 4.76 t/s 30.49.564.784 I slot print_timing: id 3 | task 6377 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.76 t/s 30.51.243.659 I slot print_timing: id 1 | task 6121 | prompt eval time = 2394.61 ms / 110 tokens ( 21.77 ms per token, 45.94 tokens per second) 30.51.243.664 I slot print_timing: id 1 | task 6121 | eval time = 86826.93 ms / 375 tokens ( 232.16 ms per token, 4.31 tokens per second) 30.51.243.665 I slot print_timing: id 1 | task 6121 | total time = 89221.54 ms / 485 tokens 30.51.243.665 I slot print_timing: id 1 | task 6121 | graphs reused = 5686 30.51.243.666 I slot print_timing: id 1 | task 6121 | graph reallocs = 0 / 0 (same size) / (changed size) 30.51.243.710 I slot release: id 1 | task 6121 | stop processing: n_tokens = 1609, truncated = 0 30.51.529.037 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.712 30.51.529.087 I slot launch_slot_: id 1 | task 6504 | processing task, is_child = 0 30.53.056.690 I slot print_timing: id 2 | task 6321 | n_gen = 180, tg = 4.26 t/s, tg_3s = 3.07 t/s 30.53.056.896 I slot print_timing: id 3 | task 6377 | n_gen = 125, tg = 4.31 t/s, tg_3s = 2.86 t/s 30.56.126.870 I slot print_timing: id 2 | task 6321 | n_gen = 193, tg = 4.26 t/s, tg_3s = 4.23 t/s 30.56.127.025 I slot print_timing: id 3 | task 6377 | n_gen = 138, tg = 4.30 t/s, tg_3s = 4.23 t/s 30.59.277.103 I slot print_timing: id 2 | task 6321 | n_gen = 208, tg = 4.29 t/s, tg_3s = 4.76 t/s 30.59.277.254 I slot print_timing: id 3 | task 6377 | n_gen = 153, tg = 4.34 t/s, tg_3s = 4.76 t/s 31.02.428.088 I slot print_timing: id 2 | task 6321 | n_gen = 223, tg = 4.32 t/s, tg_3s = 4.76 t/s 31.02.428.239 I slot print_timing: id 3 | task 6377 | n_gen = 168, tg = 4.38 t/s, tg_3s = 4.76 t/s 31.02.848.253 I slot print_timing: id 2 | task 6321 | prompt eval time = 2275.43 ms / 120 tokens ( 18.96 ms per token, 52.74 tokens per second) 31.02.848.257 I slot print_timing: id 2 | task 6321 | eval time = 51790.37 ms / 225 tokens ( 231.21 ms per token, 4.33 tokens per second) 31.02.848.257 I slot print_timing: id 2 | task 6321 | total time = 54065.79 ms / 345 tokens 31.02.848.258 I slot print_timing: id 2 | task 6321 | graphs reused = 5729 31.02.848.258 I slot print_timing: id 2 | task 6321 | graph reallocs = 0 / 0 (same size) / (changed size) 31.02.848.312 I slot release: id 2 | task 6321 | stop processing: n_tokens = 1469, truncated = 0 31.03.133.158 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.780 31.03.133.190 I slot launch_slot_: id 2 | task 6552 | processing task, is_child = 0 31.05.616.175 I slot print_timing: id 3 | task 6377 | n_gen = 174, tg = 4.19 t/s, tg_3s = 1.88 t/s 31.06.035.677 I slot print_timing: id 0 | task 6454 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 31.08.765.312 I slot print_timing: id 3 | task 6377 | n_gen = 189, tg = 4.23 t/s, tg_3s = 4.76 t/s 31.09.184.382 I slot print_timing: id 0 | task 6454 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.76 t/s 31.11.914.553 I slot print_timing: id 3 | task 6377 | n_gen = 204, tg = 4.26 t/s, tg_3s = 4.76 t/s 31.12.334.018 I slot print_timing: id 0 | task 6454 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.76 t/s 31.15.065.519 I slot print_timing: id 3 | task 6377 | n_gen = 219, tg = 4.29 t/s, tg_3s = 4.76 t/s 31.15.485.088 I slot print_timing: id 0 | task 6454 | n_gen = 145, tg = 4.25 t/s, tg_3s = 4.76 t/s 31.16.325.276 I slot print_timing: id 1 | task 6504 | n_gen = 100, tg = 4.36 t/s, tg_3s = 4.40 t/s 31.18.216.265 I slot print_timing: id 3 | task 6377 | n_gen = 234, tg = 4.32 t/s, tg_3s = 4.76 t/s 31.18.635.758 I slot print_timing: id 0 | task 6454 | n_gen = 160, tg = 4.29 t/s, tg_3s = 4.76 t/s 31.19.055.747 I slot print_timing: id 1 | task 6504 | prompt eval time = 2076.29 ms / 98 tokens ( 21.19 ms per token, 47.20 tokens per second) 31.19.055.753 I slot print_timing: id 1 | task 6504 | eval time = 25450.36 ms / 113 tokens ( 227.24 ms per token, 4.40 tokens per second) 31.19.055.753 I slot print_timing: id 1 | task 6504 | total time = 27526.65 ms / 211 tokens 31.19.055.754 I slot print_timing: id 1 | task 6504 | graphs reused = 5793 31.19.055.754 I slot print_timing: id 1 | task 6504 | graph reallocs = 0 / 0 (same size) / (changed size) 31.19.055.801 I slot release: id 1 | task 6504 | stop processing: n_tokens = 1335, truncated = 0 31.19.341.316 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.858 31.19.341.350 I slot launch_slot_: id 1 | task 6621 | processing task, is_child = 0 31.21.758.643 I slot print_timing: id 0 | task 6454 | n_gen = 165, tg = 4.08 t/s, tg_3s = 1.60 t/s 31.21.759.120 I slot print_timing: id 3 | task 6377 | n_gen = 241, tg = 4.18 t/s, tg_3s = 1.98 t/s 31.24.911.035 I slot print_timing: id 0 | task 6454 | n_gen = 180, tg = 4.13 t/s, tg_3s = 4.76 t/s 31.24.911.437 I slot print_timing: id 3 | task 6377 | n_gen = 256, tg = 4.21 t/s, tg_3s = 4.76 t/s 31.28.062.388 I slot print_timing: id 0 | task 6454 | n_gen = 195, tg = 4.17 t/s, tg_3s = 4.76 t/s 31.28.062.818 I slot print_timing: id 3 | task 6377 | n_gen = 271, tg = 4.23 t/s, tg_3s = 4.76 t/s 31.28.272.836 I slot print_timing: id 2 | task 6552 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.37 t/s 31.31.217.043 I slot print_timing: id 0 | task 6454 | n_gen = 210, tg = 4.21 t/s, tg_3s = 4.75 t/s 31.31.217.487 I slot print_timing: id 3 | task 6377 | n_gen = 286, tg = 4.26 t/s, tg_3s = 4.75 t/s 31.31.427.482 I slot print_timing: id 2 | task 6552 | n_gen = 115, tg = 4.38 t/s, tg_3s = 4.75 t/s 31.34.368.368 I slot print_timing: id 0 | task 6454 | n_gen = 225, tg = 4.24 t/s, tg_3s = 4.76 t/s 31.34.368.795 I slot print_timing: id 3 | task 6377 | n_gen = 301, tg = 4.28 t/s, tg_3s = 4.76 t/s 31.34.578.798 I slot print_timing: id 2 | task 6552 | n_gen = 130, tg = 4.42 t/s, tg_3s = 4.76 t/s 31.37.520.047 I slot print_timing: id 0 | task 6454 | n_gen = 240, tg = 4.27 t/s, tg_3s = 4.76 t/s 31.37.520.467 I slot print_timing: id 3 | task 6377 | n_gen = 316, tg = 4.30 t/s, tg_3s = 4.76 t/s 31.37.730.542 I slot print_timing: id 2 | task 6552 | n_gen = 145, tg = 4.45 t/s, tg_3s = 4.76 t/s 31.40.673.079 I slot print_timing: id 0 | task 6454 | n_gen = 255, tg = 4.30 t/s, tg_3s = 4.76 t/s 31.40.673.480 I slot print_timing: id 3 | task 6377 | n_gen = 331, tg = 4.32 t/s, tg_3s = 4.76 t/s 31.40.883.536 I slot print_timing: id 2 | task 6552 | n_gen = 160, tg = 4.48 t/s, tg_3s = 4.76 t/s 31.42.564.918 I slot print_timing: id 1 | task 6621 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 31.43.826.000 I slot print_timing: id 0 | task 6454 | n_gen = 270, tg = 4.32 t/s, tg_3s = 4.76 t/s 31.43.826.391 I slot print_timing: id 3 | task 6377 | n_gen = 346, tg = 4.34 t/s, tg_3s = 4.76 t/s 31.44.036.313 I slot print_timing: id 2 | task 6552 | n_gen = 175, tg = 4.50 t/s, tg_3s = 4.76 t/s 31.45.717.929 I slot print_timing: id 1 | task 6621 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 31.46.979.356 I slot print_timing: id 0 | task 6454 | n_gen = 285, tg = 4.34 t/s, tg_3s = 4.76 t/s 31.46.979.771 I slot print_timing: id 3 | task 6377 | n_gen = 361, tg = 4.35 t/s, tg_3s = 4.76 t/s 31.47.189.806 I slot print_timing: id 2 | task 6552 | n_gen = 190, tg = 4.52 t/s, tg_3s = 4.76 t/s 31.48.870.923 I slot print_timing: id 1 | task 6621 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 31.50.132.757 I slot print_timing: id 0 | task 6454 | n_gen = 300, tg = 4.36 t/s, tg_3s = 4.76 t/s 31.50.133.205 I slot print_timing: id 3 | task 6377 | n_gen = 376, tg = 4.37 t/s, tg_3s = 4.76 t/s 31.50.343.079 I slot print_timing: id 2 | task 6552 | n_gen = 205, tg = 4.54 t/s, tg_3s = 4.76 t/s 31.51.604.844 I slot print_timing: id 3 | task 6377 | prompt eval time = 2115.25 ms / 131 tokens ( 16.15 ms per token, 61.93 tokens per second) 31.51.604.849 I slot print_timing: id 3 | task 6377 | eval time = 87312.05 ms / 383 tokens ( 228.57 ms per token, 4.38 tokens per second) 31.51.604.850 I slot print_timing: id 3 | task 6377 | total time = 89427.30 ms / 514 tokens 31.51.604.850 I slot print_timing: id 3 | task 6377 | graphs reused = 5933 31.51.604.851 I slot print_timing: id 3 | task 6377 | graph reallocs = 0 / 0 (same size) / (changed size) 31.51.604.899 I slot release: id 3 | task 6377 | stop processing: n_tokens = 1638, truncated = 0 31.51.804.233 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.700 31.51.804.267 I slot launch_slot_: id 3 | task 6767 | processing task, is_child = 0 31.53.498.623 I slot print_timing: id 0 | task 6454 | n_gen = 309, tg = 4.28 t/s, tg_3s = 2.67 t/s 31.53.498.783 I slot print_timing: id 1 | task 6621 | n_gen = 145, tg = 4.54 t/s, tg_3s = 3.24 t/s 31.53.498.981 I slot print_timing: id 2 | task 6552 | n_gen = 213, tg = 4.41 t/s, tg_3s = 2.53 t/s 31.56.421.646 I slot print_timing: id 0 | task 6454 | prompt eval time = 1745.00 ms / 95 tokens ( 18.37 ms per token, 54.44 tokens per second) 31.56.421.651 I slot print_timing: id 0 | task 6454 | eval time = 74841.97 ms / 322 tokens ( 233.15 ms per token, 4.29 tokens per second) 31.56.421.652 I slot print_timing: id 0 | task 6454 | total time = 76586.96 ms / 417 tokens 31.56.421.653 I slot print_timing: id 0 | task 6454 | graphs reused = 5943 31.56.421.653 I slot print_timing: id 0 | task 6454 | graph reallocs = 0 / 0 (same size) / (changed size) 31.56.421.694 I slot release: id 0 | task 6454 | stop processing: n_tokens = 1541, truncated = 0 31.56.620.902 I slot print_timing: id 1 | task 6621 | n_gen = 159, tg = 4.53 t/s, tg_3s = 4.48 t/s 31.56.621.048 I slot print_timing: id 2 | task 6552 | n_gen = 227, tg = 4.41 t/s, tg_3s = 4.48 t/s 31.56.621.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.744 31.56.621.229 I slot launch_slot_: id 0 | task 6783 | processing task, is_child = 0 31.59.753.494 I slot print_timing: id 1 | task 6621 | n_gen = 166, tg = 4.34 t/s, tg_3s = 2.23 t/s 31.59.753.638 I slot print_timing: id 2 | task 6552 | n_gen = 234, tg = 4.29 t/s, tg_3s = 2.23 t/s 32.02.903.492 I slot print_timing: id 1 | task 6621 | n_gen = 181, tg = 4.37 t/s, tg_3s = 4.76 t/s 32.02.903.630 I slot print_timing: id 2 | task 6552 | n_gen = 249, tg = 4.31 t/s, tg_3s = 4.76 t/s 32.06.053.857 I slot print_timing: id 1 | task 6621 | n_gen = 196, tg = 4.40 t/s, tg_3s = 4.76 t/s 32.06.054.015 I slot print_timing: id 2 | task 6552 | n_gen = 264, tg = 4.34 t/s, tg_3s = 4.76 t/s 32.09.205.009 I slot print_timing: id 1 | task 6621 | n_gen = 211, tg = 4.43 t/s, tg_3s = 4.76 t/s 32.09.205.148 I slot print_timing: id 2 | task 6552 | n_gen = 279, tg = 4.36 t/s, tg_3s = 4.76 t/s 32.12.355.339 I slot print_timing: id 1 | task 6621 | n_gen = 226, tg = 4.45 t/s, tg_3s = 4.76 t/s 32.12.355.489 I slot print_timing: id 2 | task 6552 | n_gen = 294, tg = 4.38 t/s, tg_3s = 4.76 t/s 32.14.879.627 I slot print_timing: id 2 | task 6552 | prompt eval time = 2270.25 ms / 116 tokens ( 19.57 ms per token, 51.10 tokens per second) 32.14.879.632 I slot print_timing: id 2 | task 6552 | eval time = 69476.18 ms / 306 tokens ( 227.79 ms per token, 4.39 tokens per second) 32.14.879.633 I slot print_timing: id 2 | task 6552 | total time = 71746.43 ms / 422 tokens 32.14.879.633 I slot print_timing: id 2 | task 6552 | graphs reused = 6019 32.14.879.634 I slot print_timing: id 2 | task 6552 | graph reallocs = 0 / 0 (same size) / (changed size) 32.14.879.677 I slot release: id 2 | task 6552 | stop processing: n_tokens = 1546, truncated = 0 32.15.165.278 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.741 32.15.165.311 I slot launch_slot_: id 2 | task 6864 | processing task, is_child = 0 32.16.961.449 I slot print_timing: id 1 | task 6621 | n_gen = 240, tg = 4.33 t/s, tg_3s = 3.04 t/s 32.18.285.415 I slot print_timing: id 3 | task 6767 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.10 t/s 32.19.965.207 I slot print_timing: id 1 | task 6621 | n_gen = 253, tg = 4.33 t/s, tg_3s = 4.33 t/s 32.21.435.769 I slot print_timing: id 0 | task 6783 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 32.21.436.219 I slot print_timing: id 3 | task 6767 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.76 t/s 32.23.116.052 I slot print_timing: id 1 | task 6621 | n_gen = 268, tg = 4.35 t/s, tg_3s = 4.76 t/s 32.23.746.470 I slot print_timing: id 3 | task 6767 | prompt eval time = 2091.53 ms / 103 tokens ( 20.31 ms per token, 49.25 tokens per second) 32.23.746.472 I slot print_timing: id 3 | task 6767 | eval time = 29850.67 ms / 126 tokens ( 238.81 ms per token, 4.19 tokens per second) 32.23.746.473 I slot print_timing: id 3 | task 6767 | total time = 31942.20 ms / 229 tokens 32.23.746.474 I slot print_timing: id 3 | task 6767 | graphs reused = 6048 32.23.746.474 I slot print_timing: id 3 | task 6767 | graph reallocs = 0 / 0 (same size) / (changed size) 32.23.746.518 I slot release: id 3 | task 6767 | stop processing: n_tokens = 1353, truncated = 0 32.23.945.559 I slot print_timing: id 1 | task 6621 | prompt eval time = 2417.48 ms / 130 tokens ( 18.60 ms per token, 53.77 tokens per second) 32.23.945.564 I slot print_timing: id 1 | task 6621 | eval time = 62186.72 ms / 272 tokens ( 229.47 ms per token, 4.36 tokens per second) 32.23.945.566 I slot print_timing: id 1 | task 6621 | total time = 64604.21 ms / 402 tokens 32.23.945.566 I slot print_timing: id 1 | task 6621 | graphs reused = 6048 32.23.945.566 I slot print_timing: id 1 | task 6621 | graph reallocs = 0 / 0 (same size) / (changed size) 32.23.945.605 I slot release: id 1 | task 6621 | stop processing: n_tokens = 1526, truncated = 0 32.23.945.762 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.751 32.23.945.790 I slot launch_slot_: id 1 | task 6898 | processing task, is_child = 0 32.23.945.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 32.23.945.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 32.23.945.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 32.23.991.745 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.847 32.23.991.792 I slot launch_slot_: id 3 | task 6899 | processing task, is_child = 0 32.27.335.498 I slot print_timing: id 0 | task 6783 | n_gen = 113, tg = 3.91 t/s, tg_3s = 2.20 t/s 32.27.335.692 I slot print_timing: id 1 | task 6898 | prompt processing, n_tokens = 119, progress = 1.00, t = 3.34 s / 35.59 tokens per second 32.27.343.967 I slot print_timing: id 3 | task 6899 | prompt processing, n_tokens = 114, progress = 1.00, t = 3.34 s / 34.17 tokens per second 32.30.374.234 I slot print_timing: id 0 | task 6783 | n_gen = 125, tg = 3.91 t/s, tg_3s = 3.95 t/s 32.33.523.605 I slot print_timing: id 0 | task 6783 | n_gen = 140, tg = 3.99 t/s, tg_3s = 4.76 t/s 32.36.672.893 I slot print_timing: id 0 | task 6783 | n_gen = 155, tg = 4.06 t/s, tg_3s = 4.76 t/s 32.39.824.919 I slot print_timing: id 0 | task 6783 | n_gen = 170, tg = 4.11 t/s, tg_3s = 4.76 t/s 32.41.925.710 I slot print_timing: id 2 | task 6864 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 32.42.974.533 I slot print_timing: id 0 | task 6783 | n_gen = 185, tg = 4.16 t/s, tg_3s = 4.76 t/s 32.45.075.033 I slot print_timing: id 2 | task 6864 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.76 t/s 32.46.125.422 I slot print_timing: id 0 | task 6783 | n_gen = 200, tg = 4.20 t/s, tg_3s = 4.76 t/s 32.48.226.246 I slot print_timing: id 2 | task 6864 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.76 t/s 32.48.856.355 I slot print_timing: id 1 | task 6898 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 32.48.856.634 I slot print_timing: id 3 | task 6899 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 32.49.276.460 I slot print_timing: id 0 | task 6783 | n_gen = 215, tg = 4.23 t/s, tg_3s = 4.76 t/s 32.51.377.703 I slot print_timing: id 2 | task 6864 | n_gen = 145, tg = 4.24 t/s, tg_3s = 4.76 t/s 32.52.008.134 I slot print_timing: id 1 | task 6898 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.52.008.452 I slot print_timing: id 3 | task 6899 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.52.428.282 I slot print_timing: id 0 | task 6783 | n_gen = 230, tg = 4.26 t/s, tg_3s = 4.76 t/s 32.54.526.687 I slot print_timing: id 2 | task 6864 | n_gen = 160, tg = 4.29 t/s, tg_3s = 4.76 t/s 32.55.157.152 I slot print_timing: id 1 | task 6898 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.55.157.439 I slot print_timing: id 3 | task 6899 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.55.577.123 I slot print_timing: id 0 | task 6783 | n_gen = 245, tg = 4.29 t/s, tg_3s = 4.76 t/s 32.57.677.984 I slot print_timing: id 2 | task 6864 | n_gen = 175, tg = 4.32 t/s, tg_3s = 4.76 t/s 32.58.308.341 I slot print_timing: id 1 | task 6898 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.58.308.628 I slot print_timing: id 3 | task 6899 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 32.58.728.421 I slot print_timing: id 0 | task 6783 | n_gen = 260, tg = 4.31 t/s, tg_3s = 4.76 t/s 33.00.829.186 I slot print_timing: id 2 | task 6864 | n_gen = 190, tg = 4.36 t/s, tg_3s = 4.76 t/s 33.01.459.803 I slot print_timing: id 1 | task 6898 | n_gen = 160, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.01.460.084 I slot print_timing: id 3 | task 6899 | n_gen = 160, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.01.879.943 I slot print_timing: id 0 | task 6783 | n_gen = 275, tg = 4.34 t/s, tg_3s = 4.76 t/s 33.03.982.058 I slot print_timing: id 2 | task 6864 | n_gen = 205, tg = 4.38 t/s, tg_3s = 4.76 t/s 33.04.612.244 I slot print_timing: id 1 | task 6898 | n_gen = 175, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.04.612.546 I slot print_timing: id 3 | task 6899 | n_gen = 175, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.05.032.552 I slot print_timing: id 0 | task 6783 | n_gen = 290, tg = 4.36 t/s, tg_3s = 4.76 t/s 33.07.137.831 I slot print_timing: id 2 | task 6864 | n_gen = 220, tg = 4.41 t/s, tg_3s = 4.75 t/s 33.07.768.381 I slot print_timing: id 1 | task 6898 | n_gen = 190, tg = 4.76 t/s, tg_3s = 4.75 t/s 33.07.768.659 I slot print_timing: id 3 | task 6899 | n_gen = 190, tg = 4.76 t/s, tg_3s = 4.75 t/s 33.08.188.790 I slot print_timing: id 0 | task 6783 | n_gen = 305, tg = 4.37 t/s, tg_3s = 4.75 t/s 33.10.291.544 I slot print_timing: id 2 | task 6864 | n_gen = 235, tg = 4.43 t/s, tg_3s = 4.76 t/s 33.10.922.049 I slot print_timing: id 1 | task 6898 | n_gen = 205, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.10.922.346 I slot print_timing: id 3 | task 6899 | n_gen = 205, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.11.342.423 I slot print_timing: id 0 | task 6783 | n_gen = 320, tg = 4.39 t/s, tg_3s = 4.76 t/s 33.13.445.474 I slot print_timing: id 2 | task 6864 | n_gen = 250, tg = 4.45 t/s, tg_3s = 4.76 t/s 33.14.075.925 I slot print_timing: id 1 | task 6898 | n_gen = 220, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.14.076.233 I slot print_timing: id 3 | task 6899 | n_gen = 220, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.14.496.254 I slot print_timing: id 0 | task 6783 | n_gen = 335, tg = 4.41 t/s, tg_3s = 4.76 t/s 33.16.599.041 I slot print_timing: id 2 | task 6864 | n_gen = 265, tg = 4.46 t/s, tg_3s = 4.76 t/s 33.17.229.822 I slot print_timing: id 1 | task 6898 | n_gen = 235, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.17.230.110 I slot print_timing: id 3 | task 6899 | n_gen = 235, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.17.650.070 I slot print_timing: id 0 | task 6783 | n_gen = 350, tg = 4.42 t/s, tg_3s = 4.76 t/s 33.19.753.273 I slot print_timing: id 2 | task 6864 | n_gen = 280, tg = 4.48 t/s, tg_3s = 4.76 t/s 33.20.383.943 I slot print_timing: id 1 | task 6898 | n_gen = 250, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.20.384.238 I slot print_timing: id 3 | task 6899 | n_gen = 250, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.20.804.731 I slot print_timing: id 0 | task 6783 | n_gen = 365, tg = 4.43 t/s, tg_3s = 4.75 t/s 33.22.908.176 I slot print_timing: id 2 | task 6864 | n_gen = 295, tg = 4.49 t/s, tg_3s = 4.75 t/s 33.23.538.352 I slot print_timing: id 1 | task 6898 | n_gen = 265, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.23.538.635 I slot print_timing: id 3 | task 6899 | n_gen = 265, tg = 4.76 t/s, tg_3s = 4.76 t/s 33.23.959.023 I slot print_timing: id 0 | task 6783 | n_gen = 380, tg = 4.45 t/s, tg_3s = 4.76 t/s 33.24.799.662 I slot print_timing: id 1 | task 6898 | prompt eval time = 4070.54 ms / 123 tokens ( 33.09 ms per token, 30.22 tokens per second) 33.24.799.667 I slot print_timing: id 1 | task 6898 | eval time = 56737.32 ms / 271 tokens ( 210.14 ms per token, 4.76 tokens per second) 33.24.799.668 I slot print_timing: id 1 | task 6898 | total time = 60807.86 ms / 394 tokens 33.24.799.668 I slot print_timing: id 1 | task 6898 | graphs reused = 6316 33.24.799.669 I slot print_timing: id 1 | task 6898 | graph reallocs = 0 / 0 (same size) / (changed size) 33.24.799.711 I slot release: id 1 | task 6898 | stop processing: n_tokens = 1518, truncated = 0 33.25.085.302 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.755 33.25.085.337 I slot launch_slot_: id 1 | task 7173 | processing task, is_child = 0 33.26.604.879 I slot print_timing: id 2 | task 6864 | n_gen = 306, tg = 4.41 t/s, tg_3s = 2.98 t/s 33.26.605.080 I slot print_timing: id 3 | task 6899 | n_gen = 273, tg = 4.65 t/s, tg_3s = 2.61 t/s 33.27.152.901 I slot print_timing: id 0 | task 6783 | n_gen = 387, tg = 4.36 t/s, tg_3s = 2.19 t/s 33.29.678.456 I slot print_timing: id 2 | task 6864 | n_gen = 319, tg = 4.40 t/s, tg_3s = 4.23 t/s 33.29.678.614 I slot print_timing: id 3 | task 6899 | n_gen = 286, tg = 4.63 t/s, tg_3s = 4.23 t/s 33.30.308.740 I slot print_timing: id 0 | task 6783 | n_gen = 402, tg = 4.38 t/s, tg_3s = 4.75 t/s 33.32.832.552 I slot print_timing: id 2 | task 6864 | n_gen = 334, tg = 4.42 t/s, tg_3s = 4.76 t/s 33.32.832.697 I slot print_timing: id 3 | task 6899 | n_gen = 301, tg = 4.63 t/s, tg_3s = 4.76 t/s 33.33.463.371 I slot print_timing: id 0 | task 6783 | n_gen = 417, tg = 4.39 t/s, tg_3s = 4.75 t/s 33.35.987.251 I slot print_timing: id 2 | task 6864 | n_gen = 349, tg = 4.43 t/s, tg_3s = 4.75 t/s 33.35.987.404 I slot print_timing: id 3 | task 6899 | n_gen = 316, tg = 4.64 t/s, tg_3s = 4.75 t/s 33.36.617.962 I slot print_timing: id 0 | task 6783 | n_gen = 432, tg = 4.40 t/s, tg_3s = 4.75 t/s 33.39.141.860 I slot print_timing: id 2 | task 6864 | n_gen = 364, tg = 4.44 t/s, tg_3s = 4.75 t/s 33.39.142.016 I slot print_timing: id 3 | task 6899 | n_gen = 331, tg = 4.64 t/s, tg_3s = 4.75 t/s 33.39.772.482 I slot print_timing: id 0 | task 6783 | n_gen = 447, tg = 4.41 t/s, tg_3s = 4.76 t/s 33.42.297.434 I slot print_timing: id 2 | task 6864 | n_gen = 379, tg = 4.45 t/s, tg_3s = 4.75 t/s 33.42.297.586 I slot print_timing: id 3 | task 6899 | n_gen = 346, tg = 4.65 t/s, tg_3s = 4.75 t/s 33.42.928.296 I slot print_timing: id 0 | task 6783 | n_gen = 462, tg = 4.42 t/s, tg_3s = 4.75 t/s 33.45.453.465 I slot print_timing: id 2 | task 6864 | n_gen = 394, tg = 4.47 t/s, tg_3s = 4.75 t/s 33.45.453.634 I slot print_timing: id 3 | task 6899 | n_gen = 361, tg = 4.65 t/s, tg_3s = 4.75 t/s 33.45.663.726 I slot print_timing: id 0 | task 6783 | prompt eval time = 2079.76 ms / 122 tokens ( 17.05 ms per token, 58.66 tokens per second) 33.45.663.729 I slot print_timing: id 0 | task 6783 | eval time = 106962.74 ms / 475 tokens ( 225.66 ms per token, 4.43 tokens per second) 33.45.663.729 I slot print_timing: id 0 | task 6783 | total time = 109042.49 ms / 597 tokens 33.45.663.730 I slot print_timing: id 0 | task 6783 | graphs reused = 6403 33.45.663.730 I slot print_timing: id 0 | task 6783 | graph reallocs = 0 / 0 (same size) / (changed size) 33.45.663.775 I slot release: id 0 | task 6783 | stop processing: n_tokens = 1721, truncated = 0 33.45.863.589 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.666 33.45.863.624 I slot launch_slot_: id 0 | task 7265 | processing task, is_child = 0 33.47.822.848 I slot print_timing: id 3 | task 6899 | prompt eval time = 4063.26 ms / 118 tokens ( 34.43 ms per token, 29.04 tokens per second) 33.47.822.854 I slot print_timing: id 3 | task 6899 | eval time = 79760.16 ms / 366 tokens ( 218.52 ms per token, 4.58 tokens per second) 33.47.822.854 I slot print_timing: id 3 | task 6899 | total time = 83823.42 ms / 484 tokens 33.47.822.855 I slot print_timing: id 3 | task 6899 | graphs reused = 6404 33.47.822.855 I slot print_timing: id 3 | task 6899 | graph reallocs = 0 / 0 (same size) / (changed size) 33.47.822.903 I slot release: id 3 | task 6899 | stop processing: n_tokens = 1608, truncated = 0 33.48.021.621 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.713 33.48.021.651 I slot launch_slot_: id 3 | task 7270 | processing task, is_child = 0 33.50.090.374 I slot print_timing: id 2 | task 6864 | n_gen = 401, tg = 4.32 t/s, tg_3s = 1.51 t/s 33.51.329.165 I slot print_timing: id 1 | task 7173 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.14 t/s 33.51.539.187 I slot print_timing: id 1 | task 7173 | prompt eval time = 2067.78 ms / 101 tokens ( 20.47 ms per token, 48.84 tokens per second) 33.51.539.193 I slot print_timing: id 1 | task 7173 | eval time = 24386.06 ms / 101 tokens ( 243.86 ms per token, 4.10 tokens per second) 33.51.539.194 I slot print_timing: id 1 | task 7173 | total time = 26453.84 ms / 202 tokens 33.51.539.194 I slot print_timing: id 1 | task 7173 | graphs reused = 6408 33.51.539.195 I slot print_timing: id 1 | task 7173 | graph reallocs = 0 / 0 (same size) / (changed size) 33.51.539.244 I slot release: id 1 | task 7173 | stop processing: n_tokens = 1326, truncated = 0 33.51.824.917 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.864 33.51.824.955 I slot launch_slot_: id 1 | task 7279 | processing task, is_child = 0 33.53.345.244 I slot print_timing: id 2 | task 6864 | n_gen = 409, tg = 4.25 t/s, tg_3s = 2.46 t/s 33.56.416.236 I slot print_timing: id 2 | task 6864 | n_gen = 422, tg = 4.25 t/s, tg_3s = 4.23 t/s 33.59.565.881 I slot print_timing: id 2 | task 6864 | n_gen = 437, tg = 4.27 t/s, tg_3s = 4.76 t/s 34.02.716.865 I slot print_timing: id 2 | task 6864 | n_gen = 452, tg = 4.28 t/s, tg_3s = 4.76 t/s 34.05.866.510 I slot print_timing: id 2 | task 6864 | n_gen = 467, tg = 4.30 t/s, tg_3s = 4.76 t/s 34.07.126.613 I slot print_timing: id 1 | task 7279 | prompt eval time = 2068.88 ms / 89 tokens ( 23.25 ms per token, 43.02 tokens per second) 34.07.126.618 I slot print_timing: id 1 | task 7279 | eval time = 13232.77 ms / 64 tokens ( 210.04 ms per token, 4.76 tokens per second) 34.07.126.619 I slot print_timing: id 1 | task 7279 | total time = 15301.65 ms / 153 tokens 34.07.126.619 I slot print_timing: id 1 | task 7279 | graphs reused = 6470 34.07.126.620 I slot print_timing: id 1 | task 7279 | graph reallocs = 0 / 0 (same size) / (changed size) 34.07.126.665 I slot release: id 1 | task 7279 | stop processing: n_tokens = 1277, truncated = 0 34.07.412.119 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.897 34.07.412.155 I slot launch_slot_: id 1 | task 7346 | processing task, is_child = 0 34.08.941.671 I slot print_timing: id 2 | task 6864 | n_gen = 475, tg = 4.25 t/s, tg_3s = 2.60 t/s 34.12.014.036 I slot print_timing: id 2 | task 6864 | n_gen = 488, tg = 4.25 t/s, tg_3s = 4.23 t/s 34.13.904.284 I slot print_timing: id 0 | task 7265 | n_gen = 100, tg = 3.77 t/s, tg_3s = 3.80 t/s 34.14.744.660 I slot print_timing: id 3 | task 7270 | n_gen = 100, tg = 4.08 t/s, tg_3s = 4.12 t/s 34.15.164.716 I slot print_timing: id 2 | task 6864 | n_gen = 503, tg = 4.26 t/s, tg_3s = 4.76 t/s 34.17.055.651 I slot print_timing: id 0 | task 7265 | n_gen = 115, tg = 3.87 t/s, tg_3s = 4.76 t/s 34.17.896.923 I slot print_timing: id 3 | task 7270 | n_gen = 115, tg = 4.16 t/s, tg_3s = 4.76 t/s 34.18.317.264 I slot print_timing: id 2 | task 6864 | n_gen = 518, tg = 4.28 t/s, tg_3s = 4.76 t/s 34.19.578.680 I slot print_timing: id 2 | task 6864 | prompt eval time = 2277.03 ms / 133 tokens ( 17.12 ms per token, 58.41 tokens per second) 34.19.578.683 I slot print_timing: id 2 | task 6864 | eval time = 122136.33 ms / 524 tokens ( 233.53 ms per token, 4.28 tokens per second) 34.19.578.683 I slot print_timing: id 2 | task 6864 | total time = 124413.36 ms / 657 tokens 34.19.578.684 I slot print_timing: id 2 | task 6864 | graphs reused = 6517 34.19.578.684 I slot print_timing: id 2 | task 6864 | graph reallocs = 0 / 0 (same size) / (changed size) 34.19.578.731 I slot release: id 2 | task 6864 | stop processing: n_tokens = 1781, truncated = 0 34.19.864.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.643 34.19.864.159 I slot launch_slot_: id 2 | task 7398 | processing task, is_child = 0 34.21.320.433 I slot print_timing: id 0 | task 7265 | n_gen = 129, tg = 3.80 t/s, tg_3s = 3.28 t/s 34.21.320.811 I slot print_timing: id 3 | task 7270 | n_gen = 125, tg = 4.02 t/s, tg_3s = 2.92 t/s 34.24.324.529 I slot print_timing: id 0 | task 7265 | n_gen = 142, tg = 3.84 t/s, tg_3s = 4.33 t/s 34.24.324.939 I slot print_timing: id 3 | task 7270 | n_gen = 138, tg = 4.05 t/s, tg_3s = 4.33 t/s 34.27.472.759 I slot print_timing: id 0 | task 7265 | n_gen = 157, tg = 3.91 t/s, tg_3s = 4.76 t/s 34.27.473.196 I slot print_timing: id 3 | task 7270 | n_gen = 153, tg = 4.11 t/s, tg_3s = 4.76 t/s 34.28.732.774 I slot print_timing: id 0 | task 7265 | prompt eval time = 1745.89 ms / 95 tokens ( 18.38 ms per token, 54.41 tokens per second) 34.28.732.777 I slot print_timing: id 0 | task 7265 | eval time = 41123.26 ms / 163 tokens ( 253.85 ms per token, 3.94 tokens per second) 34.28.732.777 I slot print_timing: id 0 | task 7265 | total time = 42869.14 ms / 258 tokens 34.28.732.778 I slot print_timing: id 0 | task 7265 | graphs reused = 6549 34.28.732.778 I slot print_timing: id 0 | task 7265 | graph reallocs = 0 / 0 (same size) / (changed size) 34.28.732.823 I slot release: id 0 | task 7265 | stop processing: n_tokens = 1382, truncated = 0 34.28.931.974 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.829 34.28.932.018 I slot launch_slot_: id 0 | task 7435 | processing task, is_child = 0 34.30.618.194 I slot print_timing: id 3 | task 7270 | n_gen = 161, tg = 3.99 t/s, tg_3s = 2.54 t/s 34.33.525.261 I slot print_timing: id 1 | task 7346 | n_gen = 100, tg = 4.12 t/s, tg_3s = 4.16 t/s 34.33.735.485 I slot print_timing: id 3 | task 7270 | n_gen = 175, tg = 4.02 t/s, tg_3s = 4.49 t/s 34.36.674.243 I slot print_timing: id 1 | task 7346 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.76 t/s 34.36.884.579 I slot print_timing: id 3 | task 7270 | n_gen = 190, tg = 4.07 t/s, tg_3s = 4.76 t/s 34.39.823.303 I slot print_timing: id 1 | task 7346 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.76 t/s 34.40.033.724 I slot print_timing: id 3 | task 7270 | n_gen = 205, tg = 4.12 t/s, tg_3s = 4.76 t/s 34.40.453.666 I slot print_timing: id 2 | task 7398 | prompt eval time = 1939.14 ms / 92 tokens ( 21.08 ms per token, 47.44 tokens per second) 34.40.453.668 I slot print_timing: id 2 | task 7398 | eval time = 18650.36 ms / 82 tokens ( 230.25 ms per token, 4.34 tokens per second) 34.40.453.669 I slot print_timing: id 2 | task 7398 | total time = 20589.50 ms / 174 tokens 34.40.453.670 I slot print_timing: id 2 | task 7398 | graphs reused = 6594 34.40.453.670 I slot print_timing: id 2 | task 7398 | graph reallocs = 0 / 0 (same size) / (changed size) 34.40.453.714 I slot release: id 2 | task 7398 | stop processing: n_tokens = 1298, truncated = 0 34.40.739.259 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.883 34.40.739.305 I slot launch_slot_: id 2 | task 7484 | processing task, is_child = 0 34.43.016.311 I slot print_timing: id 1 | task 7346 | n_gen = 136, tg = 4.03 t/s, tg_3s = 1.88 t/s 34.43.229.222 I slot print_timing: id 3 | task 7270 | n_gen = 211, tg = 3.98 t/s, tg_3s = 1.88 t/s 34.46.168.705 I slot print_timing: id 1 | task 7346 | n_gen = 151, tg = 4.09 t/s, tg_3s = 4.76 t/s 34.46.378.872 I slot print_timing: id 3 | task 7270 | n_gen = 226, tg = 4.03 t/s, tg_3s = 4.76 t/s 34.49.318.182 I slot print_timing: id 1 | task 7346 | n_gen = 166, tg = 4.14 t/s, tg_3s = 4.76 t/s 34.49.528.510 I slot print_timing: id 3 | task 7270 | n_gen = 241, tg = 4.06 t/s, tg_3s = 4.76 t/s 34.52.469.090 I slot print_timing: id 1 | task 7346 | n_gen = 181, tg = 4.19 t/s, tg_3s = 4.76 t/s 34.52.679.385 I slot print_timing: id 3 | task 7270 | n_gen = 256, tg = 4.10 t/s, tg_3s = 4.76 t/s 34.53.731.945 I slot print_timing: id 0 | task 7435 | n_gen = 100, tg = 4.36 t/s, tg_3s = 4.40 t/s 34.55.621.940 I slot print_timing: id 1 | task 7346 | n_gen = 196, tg = 4.23 t/s, tg_3s = 4.76 t/s 34.55.832.244 I slot print_timing: id 3 | task 7270 | n_gen = 271, tg = 4.13 t/s, tg_3s = 4.76 t/s 34.56.882.302 I slot print_timing: id 0 | task 7435 | n_gen = 115, tg = 4.41 t/s, tg_3s = 4.76 t/s 34.58.772.918 I slot print_timing: id 1 | task 7346 | n_gen = 211, tg = 4.26 t/s, tg_3s = 4.76 t/s 34.58.983.204 I slot print_timing: id 3 | task 7270 | n_gen = 286, tg = 4.16 t/s, tg_3s = 4.76 t/s 35.00.031.639 I slot print_timing: id 0 | task 7435 | n_gen = 130, tg = 4.44 t/s, tg_3s = 4.76 t/s 35.01.922.875 I slot print_timing: id 1 | task 7346 | n_gen = 226, tg = 4.29 t/s, tg_3s = 4.76 t/s 35.02.132.978 I slot print_timing: id 3 | task 7270 | n_gen = 301, tg = 4.19 t/s, tg_3s = 4.76 t/s 35.03.183.638 I slot print_timing: id 0 | task 7435 | n_gen = 145, tg = 4.47 t/s, tg_3s = 4.76 t/s 35.03.814.185 I slot print_timing: id 2 | task 7484 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 35.05.074.611 I slot print_timing: id 1 | task 7346 | n_gen = 241, tg = 4.32 t/s, tg_3s = 4.76 t/s 35.05.285.217 I slot print_timing: id 3 | task 7270 | n_gen = 316, tg = 4.21 t/s, tg_3s = 4.76 t/s 35.06.335.610 I slot print_timing: id 0 | task 7435 | n_gen = 160, tg = 4.50 t/s, tg_3s = 4.76 t/s 35.06.966.544 I slot print_timing: id 2 | task 7484 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 35.08.228.274 I slot print_timing: id 1 | task 7346 | n_gen = 256, tg = 4.34 t/s, tg_3s = 4.76 t/s 35.08.438.663 I slot print_timing: id 3 | task 7270 | n_gen = 331, tg = 4.23 t/s, tg_3s = 4.76 t/s 35.09.488.857 I slot print_timing: id 0 | task 7435 | n_gen = 175, tg = 4.52 t/s, tg_3s = 4.76 t/s 35.10.119.643 I slot print_timing: id 2 | task 7484 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 35.11.381.165 I slot print_timing: id 1 | task 7346 | n_gen = 271, tg = 4.36 t/s, tg_3s = 4.76 t/s 35.11.591.469 I slot print_timing: id 3 | task 7270 | n_gen = 346, tg = 4.25 t/s, tg_3s = 4.76 t/s 35.12.641.907 I slot print_timing: id 0 | task 7435 | n_gen = 190, tg = 4.54 t/s, tg_3s = 4.76 t/s 35.13.272.666 I slot print_timing: id 2 | task 7484 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 35.14.533.851 I slot print_timing: id 1 | task 7346 | n_gen = 286, tg = 4.38 t/s, tg_3s = 4.76 t/s 35.14.744.371 I slot print_timing: id 3 | task 7270 | n_gen = 361, tg = 4.27 t/s, tg_3s = 4.76 t/s 35.14.954.234 I slot print_timing: id 0 | task 7435 | prompt eval time = 2071.88 ms / 113 tokens ( 18.34 ms per token, 54.54 tokens per second) 35.14.954.239 I slot print_timing: id 0 | task 7435 | eval time = 43950.33 ms / 201 tokens ( 219.75 ms per token, 4.55 tokens per second) 35.14.954.239 I slot print_timing: id 0 | task 7435 | total time = 46022.21 ms / 314 tokens 35.14.954.240 I slot print_timing: id 0 | task 7435 | graphs reused = 6744 35.14.954.240 I slot print_timing: id 0 | task 7435 | graph reallocs = 0 / 0 (same size) / (changed size) 35.14.954.285 I slot release: id 0 | task 7435 | stop processing: n_tokens = 1438, truncated = 0 35.15.153.607 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.797 35.15.153.640 I slot launch_slot_: id 0 | task 7640 | processing task, is_child = 0 35.16.507.978 I slot print_timing: id 2 | task 7484 | n_gen = 155, tg = 4.60 t/s, tg_3s = 3.09 t/s 35.17.738.031 I slot print_timing: id 1 | task 7346 | n_gen = 295, tg = 4.31 t/s, tg_3s = 2.81 t/s 35.17.948.419 I slot print_timing: id 3 | task 7270 | n_gen = 370, tg = 4.22 t/s, tg_3s = 2.81 t/s 35.19.629.679 I slot print_timing: id 2 | task 7484 | n_gen = 169, tg = 4.59 t/s, tg_3s = 4.48 t/s 35.20.890.287 I slot print_timing: id 1 | task 7346 | n_gen = 310, tg = 4.33 t/s, tg_3s = 4.76 t/s 35.21.101.006 I slot print_timing: id 3 | task 7270 | n_gen = 385, tg = 4.24 t/s, tg_3s = 4.76 t/s 35.22.782.358 I slot print_timing: id 2 | task 7484 | n_gen = 184, tg = 4.60 t/s, tg_3s = 4.76 t/s 35.23.623.174 I slot print_timing: id 1 | task 7346 | prompt eval time = 2077.83 ms / 99 tokens ( 20.99 ms per token, 47.65 tokens per second) 35.23.623.181 I slot print_timing: id 1 | task 7346 | eval time = 74133.18 ms / 323 tokens ( 230.23 ms per token, 4.34 tokens per second) 35.23.623.181 I slot print_timing: id 1 | task 7346 | total time = 76211.01 ms / 422 tokens 35.23.623.182 I slot print_timing: id 1 | task 7346 | graphs reused = 6776 35.23.623.182 I slot print_timing: id 1 | task 7346 | graph reallocs = 0 / 0 (same size) / (changed size) 35.23.623.230 I slot release: id 1 | task 7346 | stop processing: n_tokens = 1546, truncated = 0 35.23.908.539 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.741 35.23.908.573 I slot launch_slot_: id 1 | task 7676 | processing task, is_child = 0 35.26.470.672 I slot print_timing: id 2 | task 7484 | n_gen = 190, tg = 4.35 t/s, tg_3s = 1.63 t/s 35.26.470.932 I slot print_timing: id 3 | task 7270 | n_gen = 399, tg = 4.15 t/s, tg_3s = 2.61 t/s 35.29.543.856 I slot print_timing: id 2 | task 7484 | n_gen = 203, tg = 4.34 t/s, tg_3s = 4.23 t/s 35.29.544.019 I slot print_timing: id 3 | task 7270 | n_gen = 412, tg = 4.15 t/s, tg_3s = 4.23 t/s 35.32.695.390 I slot print_timing: id 2 | task 7484 | n_gen = 218, tg = 4.37 t/s, tg_3s = 4.76 t/s 35.32.695.539 I slot print_timing: id 3 | task 7270 | n_gen = 427, tg = 4.17 t/s, tg_3s = 4.76 t/s 35.34.166.313 I slot print_timing: id 0 | task 7640 | prompt eval time = 1741.71 ms / 90 tokens ( 19.35 ms per token, 51.67 tokens per second) 35.34.166.319 I slot print_timing: id 0 | task 7640 | eval time = 17270.95 ms / 70 tokens ( 250.30 ms per token, 4.00 tokens per second) 35.34.166.320 I slot print_timing: id 0 | task 7640 | total time = 19012.67 ms / 160 tokens 35.34.166.320 I slot print_timing: id 0 | task 7640 | graphs reused = 6809 35.34.166.321 I slot print_timing: id 0 | task 7640 | graph reallocs = 0 / 0 (same size) / (changed size) 35.34.166.363 I slot release: id 0 | task 7640 | stop processing: n_tokens = 1284, truncated = 0 35.34.366.026 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.893 35.34.366.053 I slot launch_slot_: id 0 | task 7714 | processing task, is_child = 0 35.36.043.871 I slot print_timing: id 2 | task 7484 | n_gen = 227, tg = 4.26 t/s, tg_3s = 2.69 t/s 35.36.044.083 I slot print_timing: id 3 | task 7270 | n_gen = 436, tg = 4.12 t/s, tg_3s = 2.69 t/s 35.39.164.614 I slot print_timing: id 2 | task 7484 | n_gen = 241, tg = 4.27 t/s, tg_3s = 4.49 t/s 35.39.164.768 I slot print_timing: id 3 | task 7270 | n_gen = 450, tg = 4.13 t/s, tg_3s = 4.49 t/s 35.42.317.447 I slot print_timing: id 2 | task 7484 | n_gen = 256, tg = 4.30 t/s, tg_3s = 4.76 t/s 35.42.317.599 I slot print_timing: id 3 | task 7270 | n_gen = 465, tg = 4.15 t/s, tg_3s = 4.76 t/s 35.43.158.755 I slot print_timing: id 3 | task 7270 | prompt eval time = 2464.77 ms / 152 tokens ( 16.22 ms per token, 61.67 tokens per second) 35.43.158.760 I slot print_timing: id 3 | task 7270 | eval time = 112672.33 ms / 469 tokens ( 240.75 ms per token, 4.15 tokens per second) 35.43.158.761 I slot print_timing: id 3 | task 7270 | total time = 115137.10 ms / 621 tokens 35.43.158.761 I slot print_timing: id 3 | task 7270 | graphs reused = 6841 35.43.158.762 I slot print_timing: id 3 | task 7270 | graph reallocs = 0 / 0 (same size) / (changed size) 35.43.158.809 I slot release: id 3 | task 7270 | stop processing: n_tokens = 1745, truncated = 0 35.43.358.180 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.657 35.43.358.212 I slot launch_slot_: id 3 | task 7750 | processing task, is_child = 0 35.45.420.653 I slot print_timing: id 2 | task 7484 | n_gen = 262, tg = 4.18 t/s, tg_3s = 1.93 t/s 35.48.551.366 I slot print_timing: id 2 | task 7484 | n_gen = 276, tg = 4.20 t/s, tg_3s = 4.47 t/s 35.51.491.747 I slot print_timing: id 1 | task 7676 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 35.51.701.845 I slot print_timing: id 2 | task 7484 | n_gen = 291, tg = 4.22 t/s, tg_3s = 4.76 t/s 35.54.645.122 I slot print_timing: id 1 | task 7676 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.76 t/s 35.54.855.478 I slot print_timing: id 2 | task 7484 | n_gen = 306, tg = 4.25 t/s, tg_3s = 4.76 t/s 35.57.796.703 I slot print_timing: id 1 | task 7676 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.76 t/s 35.58.006.590 I slot print_timing: id 2 | task 7484 | n_gen = 321, tg = 4.27 t/s, tg_3s = 4.76 t/s 35.59.267.096 I slot print_timing: id 0 | task 7714 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.38 t/s 35.59.687.125 I slot print_timing: id 0 | task 7714 | prompt eval time = 2063.54 ms / 107 tokens ( 19.29 ms per token, 51.85 tokens per second) 35.59.687.130 I slot print_timing: id 0 | task 7714 | eval time = 23257.52 ms / 102 tokens ( 230.27 ms per token, 4.34 tokens per second) 35.59.687.131 I slot print_timing: id 0 | task 7714 | total time = 25321.06 ms / 209 tokens 35.59.687.131 I slot print_timing: id 0 | task 7714 | graphs reused = 6905 35.59.687.132 I slot print_timing: id 0 | task 7714 | graph reallocs = 0 / 0 (same size) / (changed size) 35.59.687.190 I slot release: id 0 | task 7714 | stop processing: n_tokens = 1333, truncated = 0 35.59.886.927 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.860 35.59.886.965 I slot launch_slot_: id 0 | task 7820 | processing task, is_child = 0 36.01.567.208 I slot print_timing: id 1 | task 7676 | n_gen = 141, tg = 4.05 t/s, tg_3s = 2.92 t/s 36.01.567.368 I slot print_timing: id 2 | task 7484 | n_gen = 331, tg = 4.20 t/s, tg_3s = 2.81 t/s 36.04.687.373 I slot print_timing: id 1 | task 7676 | n_gen = 155, tg = 4.09 t/s, tg_3s = 4.49 t/s 36.04.687.516 I slot print_timing: id 2 | task 7484 | n_gen = 345, tg = 4.21 t/s, tg_3s = 4.49 t/s 36.07.838.251 I slot print_timing: id 1 | task 7676 | n_gen = 170, tg = 4.14 t/s, tg_3s = 4.76 t/s 36.07.838.392 I slot print_timing: id 2 | task 7484 | n_gen = 360, tg = 4.23 t/s, tg_3s = 4.76 t/s 36.08.258.886 I slot print_timing: id 3 | task 7750 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.46 t/s 36.08.887.972 I slot print_timing: id 2 | task 7484 | prompt eval time = 2277.23 ms / 118 tokens ( 19.30 ms per token, 51.82 tokens per second) 36.08.887.975 I slot print_timing: id 2 | task 7484 | eval time = 85871.43 ms / 365 tokens ( 235.91 ms per token, 4.24 tokens per second) 36.08.887.975 I slot print_timing: id 2 | task 7484 | total time = 88148.66 ms / 483 tokens 36.08.887.976 I slot print_timing: id 2 | task 7484 | graphs reused = 6938 36.08.887.976 I slot print_timing: id 2 | task 7484 | graph reallocs = 0 / 0 (same size) / (changed size) 36.08.888.028 I slot release: id 2 | task 7484 | stop processing: n_tokens = 1607, truncated = 0 36.09.173.460 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.713 36.09.173.505 I slot launch_slot_: id 2 | task 7857 | processing task, is_child = 0 36.11.314.841 I slot print_timing: id 1 | task 7676 | n_gen = 177, tg = 3.97 t/s, tg_3s = 2.01 t/s 36.11.315.046 I slot print_timing: id 3 | task 7750 | n_gen = 105, tg = 4.08 t/s, tg_3s = 1.64 t/s 36.14.320.731 I slot print_timing: id 1 | task 7676 | n_gen = 190, tg = 4.00 t/s, tg_3s = 4.32 t/s 36.14.321.009 I slot print_timing: id 3 | task 7750 | n_gen = 118, tg = 4.10 t/s, tg_3s = 4.32 t/s 36.17.470.839 I slot print_timing: id 1 | task 7676 | n_gen = 205, tg = 4.04 t/s, tg_3s = 4.76 t/s 36.17.471.143 I slot print_timing: id 3 | task 7750 | n_gen = 133, tg = 4.17 t/s, tg_3s = 4.76 t/s 36.20.620.418 I slot print_timing: id 1 | task 7676 | n_gen = 220, tg = 4.09 t/s, tg_3s = 4.76 t/s 36.20.620.704 I slot print_timing: id 3 | task 7750 | n_gen = 148, tg = 4.22 t/s, tg_3s = 4.76 t/s 36.23.771.379 I slot print_timing: id 1 | task 7676 | n_gen = 235, tg = 4.12 t/s, tg_3s = 4.76 t/s 36.23.771.690 I slot print_timing: id 3 | task 7750 | n_gen = 163, tg = 4.27 t/s, tg_3s = 4.76 t/s 36.25.031.548 I slot print_timing: id 0 | task 7820 | n_gen = 100, tg = 4.29 t/s, tg_3s = 4.33 t/s 36.26.925.173 I slot print_timing: id 1 | task 7676 | n_gen = 250, tg = 4.16 t/s, tg_3s = 4.76 t/s 36.26.925.463 I slot print_timing: id 3 | task 7750 | n_gen = 178, tg = 4.31 t/s, tg_3s = 4.76 t/s 36.28.186.548 I slot print_timing: id 0 | task 7820 | n_gen = 115, tg = 4.35 t/s, tg_3s = 4.75 t/s 36.30.077.230 I slot print_timing: id 1 | task 7676 | n_gen = 265, tg = 4.19 t/s, tg_3s = 4.76 t/s 36.30.077.526 I slot print_timing: id 3 | task 7750 | n_gen = 193, tg = 4.34 t/s, tg_3s = 4.76 t/s 36.31.337.736 I slot print_timing: id 0 | task 7820 | n_gen = 130, tg = 4.39 t/s, tg_3s = 4.76 t/s 36.32.599.520 I slot print_timing: id 2 | task 7857 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 36.33.230.509 I slot print_timing: id 1 | task 7676 | n_gen = 280, tg = 4.21 t/s, tg_3s = 4.76 t/s 36.33.230.780 I slot print_timing: id 3 | task 7750 | n_gen = 208, tg = 4.37 t/s, tg_3s = 4.76 t/s 36.34.491.843 I slot print_timing: id 0 | task 7820 | n_gen = 145, tg = 4.43 t/s, tg_3s = 4.76 t/s 36.35.753.915 I slot print_timing: id 2 | task 7857 | n_gen = 115, tg = 4.76 t/s, tg_3s = 4.76 t/s 36.36.384.740 I slot print_timing: id 1 | task 7676 | n_gen = 295, tg = 4.24 t/s, tg_3s = 4.76 t/s 36.36.385.023 I slot print_timing: id 3 | task 7750 | n_gen = 223, tg = 4.39 t/s, tg_3s = 4.76 t/s 36.37.646.092 I slot print_timing: id 0 | task 7820 | n_gen = 160, tg = 4.45 t/s, tg_3s = 4.76 t/s 36.38.907.678 I slot print_timing: id 2 | task 7857 | n_gen = 130, tg = 4.76 t/s, tg_3s = 4.76 t/s 36.39.538.391 I slot print_timing: id 1 | task 7676 | n_gen = 310, tg = 4.26 t/s, tg_3s = 4.76 t/s 36.39.538.689 I slot print_timing: id 3 | task 7750 | n_gen = 238, tg = 4.41 t/s, tg_3s = 4.76 t/s 36.40.799.769 I slot print_timing: id 0 | task 7820 | n_gen = 175, tg = 4.48 t/s, tg_3s = 4.76 t/s 36.42.061.807 I slot print_timing: id 2 | task 7857 | n_gen = 145, tg = 4.76 t/s, tg_3s = 4.76 t/s 36.42.692.793 I slot print_timing: id 1 | task 7676 | n_gen = 325, tg = 4.28 t/s, tg_3s = 4.76 t/s 36.42.693.076 I slot print_timing: id 3 | task 7750 | prompt eval time = 2460.20 ms / 147 tokens ( 16.74 ms per token, 59.75 tokens per second) 36.42.693.078 I slot print_timing: id 3 | task 7750 | eval time = 56874.66 ms / 253 tokens ( 225.69 ms per token, 4.43 tokens per second) 36.42.693.078 I slot print_timing: id 3 | task 7750 | total time = 59334.86 ms / 400 tokens 36.42.693.079 I slot print_timing: id 3 | task 7750 | graphs reused = 7083 36.42.693.079 I slot print_timing: id 3 | task 7750 | graph reallocs = 0 / 0 (same size) / (changed size) 36.42.693.129 I slot release: id 3 | task 7750 | stop processing: n_tokens = 1524, truncated = 0 36.42.892.464 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.752 36.42.892.497 I slot launch_slot_: id 3 | task 8008 | processing task, is_child = 0 36.44.590.169 I slot print_timing: id 0 | task 7820 | n_gen = 186, tg = 4.34 t/s, tg_3s = 2.90 t/s 36.45.200.061 I slot print_timing: id 2 | task 7857 | n_gen = 152, tg = 4.52 t/s, tg_3s = 2.23 t/s 36.45.830.440 I slot print_timing: id 1 | task 7676 | n_gen = 332, tg = 4.20 t/s, tg_3s = 2.23 t/s 36.47.511.593 I slot print_timing: id 0 | task 7820 | prompt eval time = 2066.77 ms / 109 tokens ( 18.96 ms per token, 52.74 tokens per second) 36.47.511.598 I slot print_timing: id 0 | task 7820 | eval time = 45557.85 ms / 199 tokens ( 230.09 ms per token, 4.35 tokens per second) 36.47.511.598 I slot print_timing: id 0 | task 7820 | total time = 47624.62 ms / 308 tokens 36.47.511.599 I slot print_timing: id 0 | task 7820 | graphs reused = 7094 36.47.511.599 I slot print_timing: id 0 | task 7820 | graph reallocs = 0 / 0 (same size) / (changed size) 36.47.511.642 I slot release: id 0 | task 7820 | stop processing: n_tokens = 1432, truncated = 0 36.47.710.954 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.800 36.47.710.990 I slot launch_slot_: id 0 | task 8024 | processing task, is_child = 0 36.49.747.605 I slot print_timing: id 1 | task 7676 | n_gen = 342, tg = 4.12 t/s, tg_3s = 2.55 t/s 36.49.747.781 I slot print_timing: id 2 | task 7857 | n_gen = 165, tg = 4.32 t/s, tg_3s = 2.86 t/s 36.52.866.562 I slot print_timing: id 1 | task 7676 | n_gen = 356, tg = 4.14 t/s, tg_3s = 4.49 t/s 36.52.866.707 I slot print_timing: id 2 | task 7857 | n_gen = 179, tg = 4.33 t/s, tg_3s = 4.49 t/s 36.54.756.534 I slot print_timing: id 1 | task 7676 | prompt eval time = 3110.85 ms / 170 tokens ( 18.30 ms per token, 54.65 tokens per second) 36.54.756.541 I slot print_timing: id 1 | task 7676 | eval time = 87737.10 ms / 365 tokens ( 241.04 ms per token, 4.15 tokens per second) 36.54.756.541 I slot print_timing: id 1 | task 7676 | total time = 90847.96 ms / 535 tokens 36.54.756.542 I slot print_timing: id 1 | task 7676 | graphs reused = 7116 36.54.756.542 I slot print_timing: id 1 | task 7676 | graph reallocs = 0 / 0 (same size) / (changed size) 36.54.756.586 I slot release: id 1 | task 7676 | stop processing: n_tokens = 1659, truncated = 0 36.55.041.176 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.691 36.55.041.221 I slot launch_slot_: id 1 | task 8050 | processing task, is_child = 0 36.56.902.479 I slot print_timing: id 2 | task 7857 | n_gen = 190, tg = 4.19 t/s, tg_3s = 2.73 t/s 36.59.971.889 I slot print_timing: id 2 | task 7857 | n_gen = 203, tg = 4.19 t/s, tg_3s = 4.24 t/s 37.03.122.284 I slot print_timing: id 2 | task 7857 | n_gen = 218, tg = 4.23 t/s, tg_3s = 4.76 t/s 37.06.272.115 I slot print_timing: id 2 | task 7857 | n_gen = 233, tg = 4.26 t/s, tg_3s = 4.76 t/s 37.09.422.023 I slot print_timing: id 2 | task 7857 | n_gen = 248, tg = 4.29 t/s, tg_3s = 4.76 t/s 37.09.841.933 I slot print_timing: id 3 | task 8008 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 37.12.573.016 I slot print_timing: id 2 | task 7857 | n_gen = 263, tg = 4.31 t/s, tg_3s = 4.76 t/s 37.12.992.357 I slot print_timing: id 0 | task 8024 | n_gen = 100, tg = 4.33 t/s, tg_3s = 4.37 t/s 37.12.992.790 I slot print_timing: id 3 | task 8008 | n_gen = 115, tg = 4.07 t/s, tg_3s = 4.76 t/s 37.14.042.711 I slot print_timing: id 3 | task 8008 | prompt eval time = 2095.13 ms / 110 tokens ( 19.05 ms per token, 52.50 tokens per second) 37.14.042.714 I slot print_timing: id 3 | task 8008 | eval time = 29055.08 ms / 120 tokens ( 244.16 ms per token, 4.10 tokens per second) 37.14.042.715 I slot print_timing: id 3 | task 8008 | total time = 31150.21 ms / 230 tokens 37.14.042.715 I slot print_timing: id 3 | task 8008 | graphs reused = 7194 37.14.042.716 I slot print_timing: id 3 | task 8008 | graph reallocs = 0 / 0 (same size) / (changed size) 37.14.042.759 I slot release: id 3 | task 8008 | stop processing: n_tokens = 1354, truncated = 0 37.14.241.915 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.846 37.14.241.946 I slot launch_slot_: id 3 | task 8133 | processing task, is_child = 0 37.15.617.852 I slot print_timing: id 2 | task 7857 | n_gen = 272, tg = 4.25 t/s, tg_3s = 2.96 t/s 37.16.013.392 I slot print_timing: id 0 | task 8024 | n_gen = 108, tg = 4.13 t/s, tg_3s = 2.65 t/s 37.18.747.113 I slot print_timing: id 2 | task 7857 | n_gen = 286, tg = 4.26 t/s, tg_3s = 4.47 t/s 37.19.166.746 I slot print_timing: id 0 | task 8024 | n_gen = 123, tg = 4.20 t/s, tg_3s = 4.76 t/s 37.19.586.916 I slot print_timing: id 1 | task 8050 | n_gen = 100, tg = 4.47 t/s, tg_3s = 4.52 t/s 37.20.426.175 I slot print_timing: id 0 | task 8024 | prompt eval time = 2422.97 ms / 134 tokens ( 18.08 ms per token, 55.30 tokens per second) 37.20.426.177 I slot print_timing: id 0 | task 8024 | eval time = 30292.21 ms / 129 tokens ( 236.66 ms per token, 4.23 tokens per second) 37.20.426.178 I slot print_timing: id 0 | task 8024 | total time = 32715.18 ms / 263 tokens 37.20.426.178 I slot print_timing: id 0 | task 8024 | graphs reused = 7214 37.20.426.179 I slot print_timing: id 0 | task 8024 | graph reallocs = 0 / 0 (same size) / (changed size) 37.20.426.224 I slot release: id 0 | task 8024 | stop processing: n_tokens = 1387, truncated = 0 37.20.626.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.826 37.20.626.108 I slot launch_slot_: id 0 | task 8158 | processing task, is_child = 0 37.22.308.591 I slot print_timing: id 2 | task 7857 | n_gen = 296, tg = 4.18 t/s, tg_3s = 2.81 t/s 37.22.694.171 I slot print_timing: id 1 | task 8050 | n_gen = 107, tg = 4.20 t/s, tg_3s = 2.25 t/s 37.25.427.340 I slot print_timing: id 2 | task 7857 | n_gen = 310, tg = 4.20 t/s, tg_3s = 4.49 t/s 37.25.847.099 I slot print_timing: id 1 | task 8050 | n_gen = 122, tg = 4.26 t/s, tg_3s = 4.76 t/s 37.28.577.225 I slot print_timing: id 2 | task 7857 | n_gen = 325, tg = 4.22 t/s, tg_3s = 4.76 t/s 37.28.996.942 I slot print_timing: id 1 | task 8050 | n_gen = 137, tg = 4.31 t/s, tg_3s = 4.76 t/s 37.31.728.073 I slot print_timing: id 2 | task 7857 | n_gen = 340, tg = 4.24 t/s, tg_3s = 4.76 t/s 37.32.147.813 I slot print_timing: id 1 | task 8050 | n_gen = 152, tg = 4.35 t/s, tg_3s = 4.76 t/s 37.34.877.529 I slot print_timing: id 2 | task 7857 | n_gen = 355, tg = 4.26 t/s, tg_3s = 4.76 t/s 37.35.297.025 I slot print_timing: id 1 | task 8050 | n_gen = 167, tg = 4.39 t/s, tg_3s = 4.76 t/s 37.38.027.865 I slot print_timing: id 2 | task 7857 | n_gen = 370, tg = 4.28 t/s, tg_3s = 4.76 t/s 37.38.448.101 I slot print_timing: id 1 | task 8050 | n_gen = 182, tg = 4.41 t/s, tg_3s = 4.76 t/s 37.38.448.386 I slot print_timing: id 3 | task 8133 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.46 t/s 37.38.868.611 I slot print_timing: id 2 | task 7857 | prompt eval time = 2625.17 ms / 139 tokens ( 18.89 ms per token, 52.95 tokens per second) 37.38.868.614 I slot print_timing: id 2 | task 7857 | eval time = 87069.93 ms / 374 tokens ( 233.43 ms per token, 4.28 tokens per second) 37.38.868.614 I slot print_timing: id 2 | task 7857 | total time = 89695.10 ms / 513 tokens 37.38.868.615 I slot print_timing: id 2 | task 7857 | graphs reused = 7291 37.38.868.615 I slot print_timing: id 2 | task 7857 | graph reallocs = 0 / 0 (same size) / (changed size) 37.38.868.660 I slot release: id 2 | task 7857 | stop processing: n_tokens = 1637, truncated = 0 37.39.153.024 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.700 37.39.153.061 I slot launch_slot_: id 2 | task 8239 | processing task, is_child = 0 37.41.512.200 I slot print_timing: id 1 | task 8050 | n_gen = 189, tg = 4.27 t/s, tg_3s = 2.28 t/s 37.41.512.490 I slot print_timing: id 3 | task 8133 | n_gen = 107, tg = 4.16 t/s, tg_3s = 2.28 t/s 37.44.661.453 I slot print_timing: id 1 | task 8050 | n_gen = 204, tg = 4.30 t/s, tg_3s = 4.76 t/s 37.44.661.735 I slot print_timing: id 3 | task 8133 | n_gen = 122, tg = 4.22 t/s, tg_3s = 4.76 t/s 37.45.079.636 I slot print_timing: id 0 | task 8158 | n_gen = 100, tg = 4.42 t/s, tg_3s = 4.47 t/s 37.47.809.284 I slot print_timing: id 1 | task 8050 | n_gen = 219, tg = 4.33 t/s, tg_3s = 4.77 t/s 37.47.809.573 I slot print_timing: id 3 | task 8133 | n_gen = 137, tg = 4.28 t/s, tg_3s = 4.77 t/s 37.48.229.176 I slot print_timing: id 0 | task 8158 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 37.50.956.317 I slot print_timing: id 1 | task 8050 | n_gen = 234, tg = 4.35 t/s, tg_3s = 4.77 t/s 37.50.956.612 I slot print_timing: id 3 | task 8133 | n_gen = 152, tg = 4.32 t/s, tg_3s = 4.77 t/s 37.51.376.234 I slot print_timing: id 0 | task 8158 | n_gen = 130, tg = 4.50 t/s, tg_3s = 4.77 t/s 37.54.105.837 I slot print_timing: id 1 | task 8050 | n_gen = 249, tg = 4.38 t/s, tg_3s = 4.76 t/s 37.54.106.120 I slot print_timing: id 3 | task 8133 | n_gen = 167, tg = 4.36 t/s, tg_3s = 4.76 t/s 37.54.525.831 I slot print_timing: id 0 | task 8158 | n_gen = 145, tg = 4.52 t/s, tg_3s = 4.76 t/s 37.57.256.203 I slot print_timing: id 1 | task 8050 | n_gen = 264, tg = 4.40 t/s, tg_3s = 4.76 t/s 37.57.256.486 I slot print_timing: id 3 | task 8133 | n_gen = 182, tg = 4.39 t/s, tg_3s = 4.76 t/s 37.57.676.566 I slot print_timing: id 0 | task 8158 | n_gen = 160, tg = 4.55 t/s, tg_3s = 4.76 t/s 38.00.406.682 I slot print_timing: id 1 | task 8050 | n_gen = 279, tg = 4.42 t/s, tg_3s = 4.76 t/s 38.00.406.982 I slot print_timing: id 3 | task 8133 | n_gen = 197, tg = 4.42 t/s, tg_3s = 4.76 t/s 38.00.826.970 I slot print_timing: id 0 | task 8158 | n_gen = 175, tg = 4.56 t/s, tg_3s = 4.76 t/s 38.01.877.624 I slot print_timing: id 2 | task 8239 | n_gen = 100, tg = 4.76 t/s, tg_3s = 4.81 t/s 38.02.086.508 I slot print_timing: id 1 | task 8050 | prompt eval time = 2409.62 ms / 122 tokens ( 19.75 ms per token, 50.63 tokens per second) 38.02.086.511 I slot print_timing: id 1 | task 8050 | eval time = 64635.65 ms / 287 tokens ( 226.00 ms per token, 4.42 tokens per second) 38.02.086.512 I slot print_timing: id 1 | task 8050 | total time = 67045.28 ms / 409 tokens 38.02.086.512 I slot print_timing: id 1 | task 8050 | graphs reused = 7390 38.02.086.512 I slot print_timing: id 1 | task 8050 | graph reallocs = 0 / 0 (same size) / (changed size) 38.02.086.561 I slot release: id 1 | task 8050 | stop processing: n_tokens = 1533, truncated = 0 38.02.371.572 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.748 38.02.371.604 I slot launch_slot_: id 1 | task 8343 | processing task, is_child = 0 38.04.218.554 I slot print_timing: id 0 | task 8158 | n_gen = 183, tg = 4.38 t/s, tg_3s = 2.36 t/s 38.04.218.902 I slot print_timing: id 3 | task 8133 | n_gen = 207, tg = 4.27 t/s, tg_3s = 2.62 t/s 38.04.979.461 I slot print_timing: id 2 | task 8239 | n_gen = 105, tg = 4.35 t/s, tg_3s = 1.61 t/s 38.07.288.883 I slot print_timing: id 0 | task 8158 | n_gen = 196, tg = 4.37 t/s, tg_3s = 4.23 t/s 38.07.289.330 I slot print_timing: id 3 | task 8133 | n_gen = 220, tg = 4.27 t/s, tg_3s = 4.23 t/s 38.08.128.897 I slot print_timing: id 2 | task 8239 | n_gen = 120, tg = 4.40 t/s, tg_3s = 4.76 t/s 38.08.759.423 I slot print_timing: id 3 | task 8133 | prompt eval time = 1771.97 ms / 96 tokens ( 18.46 ms per token, 54.18 tokens per second) 38.08.759.428 I slot print_timing: id 3 | task 8133 | eval time = 52745.50 ms / 227 tokens ( 233.39 ms per token, 4.28 tokens per second) 38.08.759.428 I slot print_timing: id 3 | task 8133 | total time = 54517.47 ms / 323 tokens 38.08.759.429 I slot print_timing: id 3 | task 8133 | graphs reused = 7408 38.08.759.429 I slot print_timing: id 3 | task 8133 | graph reallocs = 0 / 0 (same size) / (changed size) 38.08.759.475 I slot release: id 3 | task 8133 | stop processing: n_tokens = 1447, truncated = 0 38.08.958.613 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.792 38.08.958.645 I slot launch_slot_: id 3 | task 8366 | processing task, is_child = 0 38.11.364.531 I slot print_timing: id 0 | task 8158 | n_gen = 205, tg = 4.19 t/s, tg_3s = 2.21 t/s 38.11.364.878 I slot print_timing: id 2 | task 8239 | n_gen = 125, tg = 4.10 t/s, tg_3s = 1.55 t/s 38.11.762.056 I slot print_timing: id 2 | task 8239 | prompt eval time = 1936.33 ms / 101 tokens ( 19.17 ms per token, 52.16 tokens per second) 38.11.762.063 I slot print_timing: id 2 | task 8239 | eval time = 30672.66 ms / 126 tokens ( 245.38 ms per token, 4.08 tokens per second) 38.11.762.063 I slot print_timing: id 2 | task 8239 | total time = 32608.99 ms / 227 tokens 38.11.762.064 I slot print_timing: id 2 | task 8239 | graphs reused = 7408 38.11.762.064 I slot print_timing: id 2 | task 8239 | graph reallocs = 0 / 0 (same size) / (changed size) 38.11.762.107 I slot release: id 2 | task 8239 | stop processing: n_tokens = 1351, truncated = 0 38.12.046.667 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.848 38.12.046.709 I slot launch_slot_: id 2 | task 8370 | processing task, is_child = 0 38.14.524.470 I slot print_timing: id 0 | task 8158 | n_gen = 210, tg = 4.03 t/s, tg_3s = 1.58 t/s 38.17.672.536 I slot print_timing: id 0 | task 8158 | n_gen = 225, tg = 4.07 t/s, tg_3s = 4.76 t/s 38.20.820.128 I slot print_timing: id 0 | task 8158 | n_gen = 240, tg = 4.11 t/s, tg_3s = 4.77 t/s 38.23.968.829 I slot print_timing: id 0 | task 8158 | n_gen = 255, tg = 4.15 t/s, tg_3s = 4.76 t/s 38.25.018.684 I slot print_timing: id 0 | task 8158 | prompt eval time = 2067.91 ms / 111 tokens ( 18.63 ms per token, 53.68 tokens per second) 38.25.018.687 I slot print_timing: id 0 | task 8158 | eval time = 62324.66 ms / 260 tokens ( 240.64 ms per token, 4.16 tokens per second) 38.25.018.687 I slot print_timing: id 0 | task 8158 | total time = 64392.57 ms / 371 tokens 38.25.018.688 I slot print_timing: id 0 | task 8158 | graphs reused = 7458 38.25.018.688 I slot print_timing: id 0 | task 8158 | graph reallocs = 0 / 0 (same size) / (changed size) 38.25.018.735 I slot release: id 0 | task 8158 | stop processing: n_tokens = 1495, truncated = 0 38.25.218.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.767 38.25.218.226 I slot launch_slot_: id 0 | task 8425 | processing task, is_child = 0 38.31.504.000 I slot print_timing: id 1 | task 8343 | n_gen = 100, tg = 3.70 t/s, tg_3s = 3.74 t/s 38.34.652.319 I slot print_timing: id 1 | task 8343 | n_gen = 115, tg = 3.81 t/s, tg_3s = 4.76 t/s 38.36.121.065 I slot print_timing: id 3 | task 8366 | n_gen = 100, tg = 4.06 t/s, tg_3s = 4.11 t/s 38.36.750.956 I slot print_timing: id 2 | task 8370 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.46 t/s 38.37.800.068 I slot print_timing: id 1 | task 8343 | n_gen = 130, tg = 3.91 t/s, tg_3s = 4.77 t/s 38.39.268.896 I slot print_timing: id 3 | task 8366 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.77 t/s 38.39.899.041 I slot print_timing: id 2 | task 8370 | n_gen = 115, tg = 4.46 t/s, tg_3s = 4.76 t/s 38.40.948.089 I slot print_timing: id 1 | task 8343 | prompt eval time = 2395.57 ms / 108 tokens ( 22.18 ms per token, 45.08 tokens per second) 38.40.948.095 I slot print_timing: id 1 | task 8343 | eval time = 36180.91 ms / 145 tokens ( 251.26 ms per token, 3.98 tokens per second) 38.40.948.095 I slot print_timing: id 1 | task 8343 | total time = 38576.48 ms / 253 tokens 38.40.948.096 I slot print_timing: id 1 | task 8343 | graphs reused = 7523 38.40.948.096 I slot print_timing: id 1 | task 8343 | graph reallocs = 0 / 0 (same size) / (changed size) 38.40.948.142 I slot release: id 1 | task 8343 | stop processing: n_tokens = 1377, truncated = 0 38.41.232.911 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.832 38.41.232.946 I slot launch_slot_: id 1 | task 8494 | processing task, is_child = 0 38.42.756.404 I slot print_timing: id 3 | task 8366 | n_gen = 125, tg = 4.00 t/s, tg_3s = 2.87 t/s 38.43.305.148 I slot print_timing: id 2 | task 8370 | n_gen = 123, tg = 4.21 t/s, tg_3s = 2.35 t/s 38.45.827.406 I slot print_timing: id 3 | task 8366 | n_gen = 138, tg = 4.02 t/s, tg_3s = 4.23 t/s 38.46.457.458 I slot print_timing: id 2 | task 8370 | n_gen = 138, tg = 4.26 t/s, tg_3s = 4.76 t/s 38.48.977.152 I slot print_timing: id 3 | task 8366 | n_gen = 153, tg = 4.08 t/s, tg_3s = 4.76 t/s 38.49.607.181 I slot print_timing: id 2 | task 8370 | n_gen = 153, tg = 4.31 t/s, tg_3s = 4.76 t/s 38.49.817.008 I slot print_timing: id 0 | task 8425 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.44 t/s 38.52.125.318 I slot print_timing: id 3 | task 8366 | n_gen = 168, tg = 4.14 t/s, tg_3s = 4.76 t/s 38.52.755.353 I slot print_timing: id 2 | task 8370 | n_gen = 168, tg = 4.34 t/s, tg_3s = 4.76 t/s 38.52.965.092 I slot print_timing: id 0 | task 8425 | n_gen = 115, tg = 4.44 t/s, tg_3s = 4.76 t/s 38.55.274.801 I slot print_timing: id 3 | task 8366 | n_gen = 183, tg = 4.18 t/s, tg_3s = 4.76 t/s 38.55.905.052 I slot print_timing: id 2 | task 8370 | n_gen = 183, tg = 4.38 t/s, tg_3s = 4.76 t/s 38.56.114.489 I slot print_timing: id 0 | task 8425 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.76 t/s 38.57.794.866 I slot print_timing: id 1 | task 8494 | prompt eval time = 2072.06 ms / 95 tokens ( 21.81 ms per token, 45.85 tokens per second) 38.57.794.869 I slot print_timing: id 1 | task 8494 | eval time = 14489.85 ms / 70 tokens ( 210.00 ms per token, 4.76 tokens per second) 38.57.794.870 I slot print_timing: id 1 | task 8494 | total time = 16561.91 ms / 165 tokens 38.57.794.870 I slot print_timing: id 1 | task 8494 | graphs reused = 7591 38.57.794.871 I slot print_timing: id 1 | task 8494 | graph reallocs = 0 / 0 (same size) / (changed size) 38.57.794.914 I slot release: id 1 | task 8494 | stop processing: n_tokens = 1289, truncated = 0 38.58.080.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.889 38.58.080.177 I slot launch_slot_: id 1 | task 8567 | processing task, is_child = 0 39.00.289.075 I slot print_timing: id 0 | task 8425 | n_gen = 140, tg = 4.21 t/s, tg_3s = 2.40 t/s 39.00.289.235 I slot print_timing: id 2 | task 8370 | n_gen = 194, tg = 4.20 t/s, tg_3s = 2.51 t/s 39.00.289.400 I slot print_timing: id 3 | task 8366 | n_gen = 197, tg = 4.04 t/s, tg_3s = 2.79 t/s 39.03.360.148 I slot print_timing: id 0 | task 8425 | n_gen = 153, tg = 4.22 t/s, tg_3s = 4.23 t/s 39.03.360.426 I slot print_timing: id 2 | task 8370 | n_gen = 207, tg = 4.20 t/s, tg_3s = 4.23 t/s 39.03.360.571 I slot print_timing: id 3 | task 8366 | n_gen = 210, tg = 4.05 t/s, tg_3s = 4.23 t/s 39.06.511.558 I slot print_timing: id 0 | task 8425 | n_gen = 168, tg = 4.26 t/s, tg_3s = 4.76 t/s 39.06.511.829 I slot print_timing: id 2 | task 8370 | n_gen = 222, tg = 4.23 t/s, tg_3s = 4.76 t/s 39.06.511.979 I slot print_timing: id 3 | task 8366 | n_gen = 225, tg = 4.09 t/s, tg_3s = 4.76 t/s 39.09.662.067 I slot print_timing: id 0 | task 8425 | n_gen = 183, tg = 4.30 t/s, tg_3s = 4.76 t/s 39.09.662.343 I slot print_timing: id 2 | task 8370 | n_gen = 237, tg = 4.26 t/s, tg_3s = 4.76 t/s 39.09.662.493 I slot print_timing: id 3 | task 8366 | n_gen = 240, tg = 4.13 t/s, tg_3s = 4.76 t/s 39.12.604.461 I slot print_timing: id 2 | task 8370 | prompt eval time = 2265.66 ms / 110 tokens ( 20.60 ms per token, 48.55 tokens per second) 39.12.604.463 I slot print_timing: id 2 | task 8370 | eval time = 58292.08 ms / 251 tokens ( 233.17 ms per token, 4.29 tokens per second) 39.12.604.464 I slot print_timing: id 2 | task 8370 | total time = 60557.74 ms / 361 tokens 39.12.604.464 I slot print_timing: id 2 | task 8370 | graphs reused = 7645 39.12.604.465 I slot print_timing: id 2 | task 8370 | graph reallocs = 0 / 0 (same size) / (changed size) 39.12.604.514 I slot release: id 2 | task 8370 | stop processing: n_tokens = 1485, truncated = 0 39.12.890.043 I slot print_timing: id 0 | task 8425 | n_gen = 198, tg = 4.32 t/s, tg_3s = 4.65 t/s 39.12.890.338 I slot print_timing: id 3 | task 8366 | n_gen = 255, tg = 4.16 t/s, tg_3s = 4.65 t/s 39.12.890.342 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.772 39.12.890.372 I slot launch_slot_: id 2 | task 8627 | processing task, is_child = 0 39.16.096.368 I slot print_timing: id 0 | task 8425 | n_gen = 206, tg = 4.20 t/s, tg_3s = 2.50 t/s 39.16.096.796 I slot print_timing: id 3 | task 8366 | n_gen = 263, tg = 4.07 t/s, tg_3s = 2.49 t/s 39.19.246.171 I slot print_timing: id 0 | task 8425 | n_gen = 221, tg = 4.24 t/s, tg_3s = 4.76 t/s 39.19.246.596 I slot print_timing: id 3 | task 8366 | n_gen = 278, tg = 4.10 t/s, tg_3s = 4.76 t/s 39.20.924.584 I slot print_timing: id 0 | task 8425 | prompt eval time = 2085.34 ms / 128 tokens ( 16.29 ms per token, 61.38 tokens per second) 39.20.924.590 I slot print_timing: id 0 | task 8425 | eval time = 53621.01 ms / 229 tokens ( 235.18 ms per token, 4.25 tokens per second) 39.20.924.590 I slot print_timing: id 0 | task 8425 | total time = 55706.35 ms / 357 tokens 39.20.924.591 I slot print_timing: id 0 | task 8425 | graphs reused = 7673 39.20.924.591 I slot print_timing: id 0 | task 8425 | graph reallocs = 0 / 0 (same size) / (changed size) 39.20.924.635 I slot release: id 0 | task 8425 | stop processing: n_tokens = 1481, truncated = 0 39.22.303.795 I slot print_timing: id 3 | task 8366 | n_gen = 293, tg = 4.14 t/s, tg_3s = 4.91 t/s 39.23.090.148 I slot print_timing: id 1 | task 8567 | n_gen = 100, tg = 4.45 t/s, tg_3s = 4.49 t/s 39.25.449.194 I slot print_timing: id 3 | task 8366 | n_gen = 309, tg = 4.18 t/s, tg_3s = 5.09 t/s 39.26.234.295 I slot print_timing: id 1 | task 8567 | n_gen = 116, tg = 4.53 t/s, tg_3s = 5.09 t/s 39.27.808.142 I slot print_timing: id 3 | task 8366 | prompt eval time = 2803.64 ms / 166 tokens ( 16.89 ms per token, 59.21 tokens per second) 39.27.808.145 I slot print_timing: id 3 | task 8366 | eval time = 76045.85 ms / 321 tokens ( 237.64 ms per token, 4.21 tokens per second) 39.27.808.145 I slot print_timing: id 3 | task 8366 | total time = 78849.49 ms / 487 tokens 39.27.808.146 I slot print_timing: id 3 | task 8366 | graphs reused = 7707 39.27.808.146 I slot print_timing: id 3 | task 8366 | graph reallocs = 0 / 0 (same size) / (changed size) 39.27.808.189 I slot release: id 3 | task 8366 | stop processing: n_tokens = 1611, truncated = 0 39.29.272.259 I slot print_timing: id 1 | task 8567 | n_gen = 132, tg = 4.61 t/s, tg_3s = 5.27 t/s 39.31.466.023 I slot print_timing: id 2 | task 8627 | prompt eval time = 1943.95 ms / 96 tokens ( 20.25 ms per token, 49.38 tokens per second) 39.31.466.025 I slot print_timing: id 2 | task 8627 | eval time = 16631.69 ms / 85 tokens ( 198.00 ms per token, 5.05 tokens per second) 39.31.466.026 I slot print_timing: id 2 | task 8627 | total time = 18575.64 ms / 181 tokens 39.31.466.026 I slot print_timing: id 2 | task 8627 | graphs reused = 7726 39.31.466.027 I slot print_timing: id 2 | task 8627 | graph reallocs = 0 / 0 (same size) / (changed size) 39.31.466.066 I slot release: id 2 | task 8627 | stop processing: n_tokens = 1305, truncated = 0 39.32.366.863 I slot print_timing: id 1 | task 8567 | n_gen = 153, tg = 4.82 t/s, tg_3s = 6.79 t/s 39.35.456.444 I slot print_timing: id 1 | task 8567 | n_gen = 184, tg = 5.29 t/s, tg_3s = 10.03 t/s 39.38.546.090 I slot print_timing: id 1 | task 8567 | n_gen = 215, tg = 5.68 t/s, tg_3s = 10.03 t/s 39.41.636.520 I slot print_timing: id 1 | task 8567 | n_gen = 246, tg = 6.01 t/s, tg_3s = 10.03 t/s 39.44.731.524 I slot print_timing: id 1 | task 8567 | n_gen = 277, tg = 6.29 t/s, tg_3s = 10.02 t/s 39.47.623.739 I slot print_timing: id 1 | task 8567 | prompt eval time = 2758.25 ms / 142 tokens ( 19.42 ms per token, 51.48 tokens per second) 39.47.623.742 I slot print_timing: id 1 | task 8567 | eval time = 46785.31 ms / 306 tokens ( 153.39 ms per token, 6.52 tokens per second) 39.47.623.743 I slot print_timing: id 1 | task 8567 | total time = 49543.56 ms / 448 tokens 39.47.623.743 I slot print_timing: id 1 | task 8567 | graphs reused = 7886 39.47.623.744 I slot print_timing: id 1 | task 8567 | graph reallocs = 0 / 0 (same size) / (changed size) 39.47.623.783 I slot release: id 1 | task 8567 | stop processing: n_tokens = 1572, truncated = 0 39.47.639.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1481, t_last = 81156666440 39.47.639.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 39.47.639.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 39.47.692.498 I slot launch_slot_: id 0 | task 8876 | processing task, is_child = 0 39.47.692.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 39.47.692.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 39.47.692.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.882 MiB) 39.47.745.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 39.47.745.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 39.47.745.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.193 MiB) 39.47.791.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 39.47.791.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 39.47.791.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 39.47.840.824 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 81163549994 39.47.840.963 I slot launch_slot_: id 3 | task 8877 | processing task, is_child = 0 39.47.841.091 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1305, t_last = 81167207871 39.47.841.174 I slot launch_slot_: id 2 | task 8878 | processing task, is_child = 0 39.47.841.241 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1572, t_last = 81183365588 39.47.841.334 I slot launch_slot_: id 1 | task 8879 | processing task, is_child = 0 39.55.115.333 I slot print_timing: id 0 | task 8876 | prompt processing, n_tokens = 124, progress = 0.16, t = 7.27 s / 17.05 tokens per second 39.55.418.912 I slot print_timing: id 1 | task 8879 | prompt processing, n_tokens = 168, progress = 0.17, t = 7.27 s / 23.10 tokens per second 39.55.423.764 I slot print_timing: id 2 | task 8878 | prompt processing, n_tokens = 154, progress = 0.16, t = 7.27 s / 21.17 tokens per second 39.55.428.327 I slot print_timing: id 3 | task 8877 | prompt processing, n_tokens = 137, progress = 0.17, t = 7.27 s / 18.84 tokens per second 40.01.798.606 I slot print_timing: id 0 | task 8876 | prompt processing, n_tokens = 263, progress = 0.34, t = 13.96 s / 18.84 tokens per second 40.02.935.160 I slot print_timing: id 1 | task 8879 | prompt processing, n_tokens = 387, progress = 0.39, t = 13.96 s / 27.73 tokens per second 40.02.935.171 I slot print_timing: id 2 | task 8878 | prompt processing, n_tokens = 279, progress = 0.29, t = 13.96 s / 19.99 tokens per second 40.02.935.179 I slot print_timing: id 3 | task 8877 | prompt processing, n_tokens = 261, progress = 0.32, t = 13.96 s / 18.70 tokens per second 40.10.207.608 I slot print_timing: id 0 | task 8876 | prompt processing, n_tokens = 656, progress = 0.84, t = 22.37 s / 29.33 tokens per second 40.11.337.998 I slot print_timing: id 1 | task 8879 | prompt processing, n_tokens = 471, progress = 0.48, t = 22.37 s / 21.06 tokens per second 40.11.342.411 I slot print_timing: id 2 | task 8878 | prompt processing, n_tokens = 436, progress = 0.46, t = 22.37 s / 19.49 tokens per second 40.11.346.832 I slot print_timing: id 3 | task 8877 | prompt processing, n_tokens = 290, progress = 0.36, t = 22.37 s / 12.97 tokens per second 40.25.992.164 I slot print_timing: id 0 | task 8876 | prompt processing, n_tokens = 775, progress = 0.99, t = 38.15 s / 20.31 tokens per second 40.26.174.933 I slot print_timing: id 1 | task 8879 | prompt processing, n_tokens = 877, progress = 0.89, t = 38.15 s / 22.99 tokens per second 40.26.179.496 I slot print_timing: id 2 | task 8878 | prompt processing, n_tokens = 835, progress = 0.88, t = 38.15 s / 21.89 tokens per second 40.26.184.113 I slot print_timing: id 3 | task 8877 | prompt processing, n_tokens = 642, progress = 0.80, t = 38.15 s / 16.83 tokens per second 40.31.299.720 I slot print_timing: id 1 | task 8879 | prompt processing, n_tokens = 983, progress = 1.00, t = 43.46 s / 22.62 tokens per second 40.31.306.341 I slot print_timing: id 2 | task 8878 | prompt processing, n_tokens = 948, progress = 1.00, t = 43.46 s / 21.81 tokens per second 40.31.318.500 I slot print_timing: id 3 | task 8877 | prompt processing, n_tokens = 802, progress = 1.00, t = 43.46 s / 18.45 tokens per second 40.31.868.930 I slot print_timing: id 0 | task 8876 | prompt eval time = 43458.37 ms / 779 tokens ( 55.79 ms per token, 17.93 tokens per second) 40.31.868.935 I slot print_timing: id 0 | task 8876 | eval time = 569.21 ms / 2 tokens ( 569.21 ms per token, 1.76 tokens per second) 40.31.868.935 I slot print_timing: id 0 | task 8876 | total time = 44027.58 ms / 781 tokens 40.31.868.936 I slot print_timing: id 0 | task 8876 | graphs reused = 7886 40.31.868.936 I slot print_timing: id 0 | task 8876 | graph reallocs = 0 / 0 (same size) / (changed size) 40.31.868.971 I slot release: id 0 | task 8876 | stop processing: n_tokens = 780, truncated = 0 40.32.066.887 I slot print_timing: id 1 | task 8879 | prompt eval time = 44027.72 ms / 987 tokens ( 44.61 ms per token, 22.42 tokens per second) 40.32.066.892 I slot print_timing: id 1 | task 8879 | eval time = 197.71 ms / 2 tokens ( 197.71 ms per token, 5.06 tokens per second) 40.32.066.893 I slot print_timing: id 1 | task 8879 | total time = 44225.43 ms / 989 tokens 40.32.066.894 I slot print_timing: id 1 | task 8879 | graphs reused = 7886 40.32.066.894 I slot print_timing: id 1 | task 8879 | graph reallocs = 0 / 0 (same size) / (changed size) 40.32.066.934 I slot release: id 1 | task 8879 | stop processing: n_tokens = 988, truncated = 0 40.32.067.099 I slot print_timing: id 2 | task 8878 | prompt eval time = 44027.82 ms / 952 tokens ( 46.25 ms per token, 21.62 tokens per second) 40.32.067.100 I slot print_timing: id 2 | task 8878 | eval time = 197.74 ms / 2 tokens ( 197.74 ms per token, 5.06 tokens per second) 40.32.067.100 I slot print_timing: id 2 | task 8878 | total time = 44225.55 ms / 954 tokens 40.32.067.101 I slot print_timing: id 2 | task 8878 | graphs reused = 7886 40.32.067.101 I slot print_timing: id 2 | task 8878 | graph reallocs = 0 / 0 (same size) / (changed size) 40.32.067.131 I slot release: id 2 | task 8878 | stop processing: n_tokens = 953, truncated = 0 40.32.067.293 I slot print_timing: id 3 | task 8877 | prompt eval time = 44028.06 ms / 806 tokens ( 54.63 ms per token, 18.31 tokens per second) 40.32.067.294 I slot print_timing: id 3 | task 8877 | eval time = 197.59 ms / 2 tokens ( 197.59 ms per token, 5.06 tokens per second) 40.32.067.294 I slot print_timing: id 3 | task 8877 | total time = 44225.65 ms / 808 tokens 40.32.067.295 I slot print_timing: id 3 | task 8877 | graphs reused = 7886 40.32.067.295 I slot print_timing: id 3 | task 8877 | graph reallocs = 0 / 0 (same size) / (changed size) 40.32.067.321 I slot release: id 3 | task 8877 | stop processing: n_tokens = 807, truncated = 0 40.32.067.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 81227610776 40.32.067.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 40.32.067.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.943 MiB) 40.32.100.168 I slot launch_slot_: id 0 | task 8887 | processing task, is_child = 0 40.32.100.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 40.32.100.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 40.32.100.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 40.32.132.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.819 MiB) 40.32.132.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.755 MiB) 40.32.165.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.631 MiB) 40.32.165.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 40.32.165.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 40.32.197.153 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 81227808739 40.32.197.273 I slot launch_slot_: id 1 | task 8888 | processing task, is_child = 0 40.32.197.362 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 81227808936 40.32.197.437 I slot launch_slot_: id 2 | task 8889 | processing task, is_child = 0 40.32.197.481 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 81227809126 40.32.197.538 I slot launch_slot_: id 3 | task 8890 | processing task, is_child = 0 40.43.316.135 I slot print_timing: id 0 | task 8887 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.12 s / 23.38 tokens per second 40.43.316.146 I slot print_timing: id 1 | task 8888 | prompt processing, n_tokens = 260, progress = 0.31, t = 11.12 s / 23.38 tokens per second 40.43.316.152 I slot print_timing: id 2 | task 8889 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.12 s / 23.38 tokens per second 40.43.316.158 I slot print_timing: id 3 | task 8890 | prompt processing, n_tokens = 260, progress = 0.30, t = 11.12 s / 23.38 tokens per second 40.46.683.254 I slot print_timing: id 0 | task 8887 | prompt processing, n_tokens = 285, progress = 0.36, t = 14.49 s / 19.67 tokens per second 40.47.454.065 I slot print_timing: id 1 | task 8888 | prompt processing, n_tokens = 330, progress = 0.39, t = 14.49 s / 22.78 tokens per second 40.47.458.493 I slot print_timing: id 2 | task 8889 | prompt processing, n_tokens = 288, progress = 0.36, t = 14.49 s / 19.88 tokens per second 40.47.462.924 I slot print_timing: id 3 | task 8890 | prompt processing, n_tokens = 339, progress = 0.40, t = 14.49 s / 23.40 tokens per second 41.04.856.765 I slot print_timing: id 0 | task 8887 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.66 s / 21.31 tokens per second 41.05.622.760 I slot print_timing: id 1 | task 8888 | prompt processing, n_tokens = 696, progress = 0.82, t = 32.66 s / 21.31 tokens per second 41.05.627.204 I slot print_timing: id 2 | task 8889 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.66 s / 21.31 tokens per second 41.05.631.578 I slot print_timing: id 3 | task 8890 | prompt processing, n_tokens = 696, progress = 0.81, t = 32.66 s / 21.31 tokens per second 41.11.498.682 I slot print_timing: id 0 | task 8887 | prompt processing, n_tokens = 797, progress = 1.00, t = 39.30 s / 20.28 tokens per second 41.12.274.860 I slot print_timing: id 1 | task 8888 | prompt processing, n_tokens = 842, progress = 1.00, t = 39.30 s / 21.42 tokens per second 41.12.288.479 I slot print_timing: id 2 | task 8889 | prompt processing, n_tokens = 800, progress = 1.00, t = 39.30 s / 20.36 tokens per second 41.12.301.955 I slot print_timing: id 3 | task 8890 | prompt processing, n_tokens = 851, progress = 1.00, t = 39.30 s / 21.65 tokens per second 41.12.894.312 I slot print_timing: id 0 | task 8887 | prompt eval time = 40484.77 ms / 801 tokens ( 50.54 ms per token, 19.79 tokens per second) 41.12.894.316 I slot print_timing: id 0 | task 8887 | eval time = 212.00 ms / 2 tokens ( 212.00 ms per token, 4.72 tokens per second) 41.12.894.316 I slot print_timing: id 0 | task 8887 | total time = 40696.76 ms / 803 tokens 41.12.894.317 I slot print_timing: id 0 | task 8887 | graphs reused = 7886 41.12.894.317 I slot print_timing: id 0 | task 8887 | graph reallocs = 0 / 0 (same size) / (changed size) 41.12.894.354 I slot release: id 0 | task 8887 | stop processing: n_tokens = 802, truncated = 0 41.12.894.504 I slot print_timing: id 1 | task 8888 | prompt eval time = 40484.90 ms / 846 tokens ( 47.85 ms per token, 20.90 tokens per second) 41.12.894.511 I slot print_timing: id 1 | task 8888 | eval time = 211.99 ms / 2 tokens ( 211.99 ms per token, 4.72 tokens per second) 41.12.894.512 I slot print_timing: id 1 | task 8888 | total time = 40696.89 ms / 848 tokens 41.12.894.512 I slot print_timing: id 1 | task 8888 | graphs reused = 7886 41.12.894.512 I slot print_timing: id 1 | task 8888 | graph reallocs = 0 / 0 (same size) / (changed size) 41.12.894.538 I slot release: id 1 | task 8888 | stop processing: n_tokens = 847, truncated = 0 41.12.894.770 I slot print_timing: id 2 | task 8889 | prompt eval time = 40485.17 ms / 804 tokens ( 50.35 ms per token, 19.86 tokens per second) 41.12.894.772 I slot print_timing: id 2 | task 8889 | eval time = 211.91 ms / 2 tokens ( 211.91 ms per token, 4.72 tokens per second) 41.12.894.772 I slot print_timing: id 2 | task 8889 | total time = 40697.09 ms / 806 tokens 41.12.894.773 I slot print_timing: id 2 | task 8889 | graphs reused = 7886 41.12.894.773 I slot print_timing: id 2 | task 8889 | graph reallocs = 0 / 0 (same size) / (changed size) 41.12.894.793 I slot release: id 2 | task 8889 | stop processing: n_tokens = 805, truncated = 0 41.12.894.966 I slot print_timing: id 3 | task 8890 | prompt eval time = 40485.58 ms / 855 tokens ( 47.35 ms per token, 21.12 tokens per second) 41.12.894.970 I slot print_timing: id 3 | task 8890 | eval time = 211.64 ms / 2 tokens ( 211.64 ms per token, 4.73 tokens per second) 41.12.894.970 I slot print_timing: id 3 | task 8890 | total time = 40697.22 ms / 857 tokens 41.12.894.970 I slot print_timing: id 3 | task 8890 | graphs reused = 7886 41.12.894.970 I slot print_timing: id 3 | task 8890 | graph reallocs = 0 / 0 (same size) / (changed size) 41.12.894.990 I slot release: id 3 | task 8890 | stop processing: n_tokens = 856, truncated = 0 41.12.903.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 81268636159 41.12.903.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 41.12.903.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 41.12.903.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.724 MiB) 41.12.922.685 I slot launch_slot_: id 0 | task 8898 | processing task, is_child = 0 41.12.954.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 840.727 MiB) 41.12.972.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 846.417 MiB) 41.12.992.354 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.855 41.12.992.411 I slot launch_slot_: id 1 | task 8899 | processing task, is_child = 0 41.12.992.498 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 81268636598 41.12.992.566 I slot launch_slot_: id 2 | task 8900 | processing task, is_child = 0 41.12.992.611 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 81268636795 41.12.992.678 I slot launch_slot_: id 3 | task 8901 | processing task, is_child = 0 41.19.510.571 I slot print_timing: id 0 | task 8898 | prompt processing, n_tokens = 171, progress = 0.18, t = 6.52 s / 26.24 tokens per second 41.20.661.709 I slot print_timing: id 1 | task 8899 | prompt processing, n_tokens = 125, progress = 1.00, t = 6.52 s / 19.18 tokens per second 41.20.666.329 I slot print_timing: id 2 | task 8900 | prompt processing, n_tokens = 160, progress = 0.18, t = 6.51 s / 24.58 tokens per second 41.20.670.923 I slot print_timing: id 3 | task 8901 | prompt processing, n_tokens = 160, progress = 0.18, t = 6.51 s / 24.58 tokens per second 41.27.482.309 I slot print_timing: id 0 | task 8898 | prompt processing, n_tokens = 340, progress = 0.35, t = 14.49 s / 23.47 tokens per second 41.27.482.321 I slot print_timing: id 2 | task 8900 | prompt processing, n_tokens = 342, progress = 0.38, t = 14.48 s / 23.62 tokens per second 41.27.482.326 I slot print_timing: id 3 | task 8901 | prompt processing, n_tokens = 342, progress = 0.39, t = 14.48 s / 23.62 tokens per second 41.30.219.421 I slot print_timing: id 1 | task 8899 | prompt eval time = 14489.54 ms / 129 tokens ( 112.32 ms per token, 8.90 tokens per second) 41.30.219.424 I slot print_timing: id 1 | task 8899 | eval time = 2737.12 ms / 2 tokens ( 2737.12 ms per token, 0.37 tokens per second) 41.30.219.424 I slot print_timing: id 1 | task 8899 | total time = 17226.66 ms / 131 tokens 41.30.219.424 I slot print_timing: id 1 | task 8899 | graphs reused = 7886 41.30.219.425 I slot print_timing: id 1 | task 8899 | graph reallocs = 0 / 0 (same size) / (changed size) 41.30.219.467 I slot release: id 1 | task 8899 | stop processing: n_tokens = 826, truncated = 0 41.30.219.478 I slot print_timing: id 0 | task 8898 | prompt processing, n_tokens = 447, progress = 0.46, t = 17.23 s / 25.95 tokens per second 41.30.226.034 I slot print_timing: id 2 | task 8900 | prompt processing, n_tokens = 380, progress = 0.42, t = 17.22 s / 22.07 tokens per second 41.30.231.007 I slot print_timing: id 3 | task 8901 | prompt processing, n_tokens = 364, progress = 0.41, t = 17.22 s / 21.14 tokens per second 41.43.138.362 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 81285961272 41.43.138.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.723 MiB) 41.43.451.696 I slot launch_slot_: id 1 | task 8906 | processing task, is_child = 0 41.43.451.709 I slot print_timing: id 0 | task 8898 | prompt processing, n_tokens = 831, progress = 0.86, t = 30.15 s / 27.57 tokens per second 41.43.456.199 I slot print_timing: id 2 | task 8900 | prompt processing, n_tokens = 754, progress = 0.84, t = 30.14 s / 25.02 tokens per second 41.43.460.604 I slot print_timing: id 3 | task 8901 | prompt processing, n_tokens = 754, progress = 0.86, t = 30.14 s / 25.02 tokens per second 41.50.104.513 I slot print_timing: id 0 | task 8898 | prompt processing, n_tokens = 959, progress = 1.00, t = 37.11 s / 25.84 tokens per second 41.50.869.088 I slot print_timing: id 1 | task 8906 | prompt processing, n_tokens = 182, progress = 0.18, t = 6.65 s / 27.38 tokens per second 41.50.873.540 I slot print_timing: id 2 | task 8900 | prompt processing, n_tokens = 892, progress = 1.00, t = 37.10 s / 24.04 tokens per second 41.50.878.068 I slot print_timing: id 3 | task 8901 | prompt processing, n_tokens = 876, progress = 1.00, t = 37.10 s / 23.61 tokens per second 41.53.798.873 I slot print_timing: id 1 | task 8906 | prompt processing, n_tokens = 403, progress = 0.41, t = 10.34 s / 38.97 tokens per second 41.55.285.527 I slot print_timing: id 0 | task 8898 | prompt eval time = 40805.66 ms / 963 tokens ( 42.37 ms per token, 23.60 tokens per second) 41.55.285.533 I slot print_timing: id 0 | task 8898 | eval time = 1487.17 ms / 2 tokens ( 1487.17 ms per token, 0.67 tokens per second) 41.55.285.533 I slot print_timing: id 0 | task 8898 | total time = 42292.84 ms / 965 tokens 41.55.285.534 I slot print_timing: id 0 | task 8898 | graphs reused = 7886 41.55.285.534 I slot print_timing: id 0 | task 8898 | graph reallocs = 0 / 0 (same size) / (changed size) 41.55.285.576 I slot release: id 0 | task 8898 | stop processing: n_tokens = 964, truncated = 0 41.55.285.736 I slot print_timing: id 2 | task 8900 | prompt eval time = 40798.34 ms / 896 tokens ( 45.53 ms per token, 21.96 tokens per second) 41.55.285.740 I slot print_timing: id 2 | task 8900 | eval time = 1487.08 ms / 2 tokens ( 1487.08 ms per token, 0.67 tokens per second) 41.55.285.741 I slot print_timing: id 2 | task 8900 | total time = 42285.42 ms / 898 tokens 41.55.285.741 I slot print_timing: id 2 | task 8900 | graphs reused = 7886 41.55.285.741 I slot print_timing: id 2 | task 8900 | graph reallocs = 0 / 0 (same size) / (changed size) 41.55.285.771 I slot release: id 2 | task 8900 | stop processing: n_tokens = 897, truncated = 0 41.55.286.032 I slot print_timing: id 3 | task 8901 | prompt eval time = 40798.49 ms / 880 tokens ( 46.36 ms per token, 21.57 tokens per second) 41.55.286.034 I slot print_timing: id 3 | task 8901 | eval time = 1487.16 ms / 2 tokens ( 1487.16 ms per token, 0.67 tokens per second) 41.55.286.034 I slot print_timing: id 3 | task 8901 | total time = 42285.65 ms / 882 tokens 41.55.286.034 I slot print_timing: id 3 | task 8901 | graphs reused = 7886 41.55.286.035 I slot print_timing: id 3 | task 8901 | graph reallocs = 0 / 0 (same size) / (changed size) 41.55.286.058 I slot release: id 3 | task 8901 | stop processing: n_tokens = 881, truncated = 0 41.55.286.065 I slot print_timing: id 1 | task 8906 | prompt processing, n_tokens = 471, progress = 0.48, t = 11.83 s / 39.82 tokens per second 41.55.297.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 81311027381 41.55.297.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 848.855 MiB) 41.59.980.924 I slot launch_slot_: id 0 | task 8911 | processing task, is_child = 0 41.59.980.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.899 MiB) 42.00.011.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 42.00.030.850 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 81311027576 42.00.030.962 I slot launch_slot_: id 2 | task 8912 | processing task, is_child = 0 42.00.031.009 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 81311027863 42.00.031.078 I slot launch_slot_: id 3 | task 8913 | processing task, is_child = 0 42.00.031.163 I slot print_timing: id 1 | task 8906 | prompt processing, n_tokens = 872, progress = 0.88, t = 11.84 s / 73.64 tokens per second 42.06.249.442 I slot print_timing: id 0 | task 8911 | prompt processing, n_tokens = 182, progress = 0.18, t = 6.22 s / 29.27 tokens per second 42.07.019.952 I slot print_timing: id 1 | task 8906 | prompt processing, n_tokens = 983, progress = 1.00, t = 22.79 s / 43.13 tokens per second 42.07.024.459 I slot print_timing: id 2 | task 8912 | prompt processing, n_tokens = 129, progress = 0.14, t = 6.21 s / 20.76 tokens per second 42.07.028.878 I slot print_timing: id 3 | task 8913 | prompt processing, n_tokens = 129, progress = 0.07, t = 6.21 s / 20.76 tokens per second 42.13.534.490 I slot print_timing: id 0 | task 8911 | prompt processing, n_tokens = 403, progress = 0.39, t = 13.50 s / 29.84 tokens per second 42.13.534.506 I slot print_timing: id 2 | task 8912 | prompt processing, n_tokens = 283, progress = 0.31, t = 13.50 s / 20.97 tokens per second 42.13.534.513 I slot print_timing: id 3 | task 8913 | prompt processing, n_tokens = 283, progress = 0.16, t = 13.50 s / 20.97 tokens per second 42.22.060.627 I slot print_timing: id 1 | task 8906 | prompt eval time = 30078.34 ms / 987 tokens ( 30.47 ms per token, 32.81 tokens per second) 42.22.060.632 I slot print_timing: id 1 | task 8906 | eval time = 8526.15 ms / 2 tokens ( 8526.15 ms per token, 0.12 tokens per second) 42.22.060.632 I slot print_timing: id 1 | task 8906 | total time = 38604.48 ms / 989 tokens 42.22.060.633 I slot print_timing: id 1 | task 8906 | graphs reused = 7886 42.22.060.633 I slot print_timing: id 1 | task 8906 | graph reallocs = 0 / 0 (same size) / (changed size) 42.22.060.672 I slot release: id 1 | task 8906 | stop processing: n_tokens = 988, truncated = 0 42.22.060.688 I slot print_timing: id 0 | task 8911 | prompt processing, n_tokens = 506, progress = 0.50, t = 22.03 s / 22.97 tokens per second 42.22.065.859 I slot print_timing: id 2 | task 8912 | prompt processing, n_tokens = 408, progress = 0.44, t = 22.02 s / 18.52 tokens per second 42.22.070.944 I slot print_timing: id 3 | task 8913 | prompt processing, n_tokens = 753, progress = 0.42, t = 22.02 s / 34.19 tokens per second 42.34.287.918 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 81337802477 42.34.287.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 42.36.482.122 I slot launch_slot_: id 1 | task 8918 | processing task, is_child = 0 42.36.482.139 I slot print_timing: id 0 | task 8911 | prompt processing, n_tokens = 872, progress = 0.85, t = 34.26 s / 25.45 tokens per second 42.36.486.666 I slot print_timing: id 2 | task 8912 | prompt processing, n_tokens = 753, progress = 0.81, t = 34.25 s / 21.98 tokens per second 42.36.491.056 I slot print_timing: id 3 | task 8913 | prompt processing, n_tokens = 1264, progress = 0.71, t = 34.25 s / 36.90 tokens per second 42.44.018.603 I slot print_timing: id 0 | task 8911 | prompt processing, n_tokens = 1018, progress = 1.00, t = 43.99 s / 23.14 tokens per second 42.48.049.992 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 129, progress = 0.14, t = 7.53 s / 17.13 tokens per second 42.48.054.798 I slot print_timing: id 2 | task 8912 | prompt processing, n_tokens = 920, progress = 1.00, t = 43.98 s / 20.92 tokens per second 42.48.059.314 I slot print_timing: id 3 | task 8913 | prompt processing, n_tokens = 1776, progress = 1.00, t = 43.98 s / 40.38 tokens per second 42.50.259.778 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 283, progress = 0.30, t = 13.77 s / 20.55 tokens per second 42.52.443.648 I slot print_timing: id 0 | task 8911 | prompt eval time = 50228.26 ms / 1022 tokens ( 49.15 ms per token, 20.35 tokens per second) 42.52.443.654 I slot print_timing: id 0 | task 8911 | eval time = 2184.30 ms / 2 tokens ( 2184.30 ms per token, 0.46 tokens per second) 42.52.443.655 I slot print_timing: id 0 | task 8911 | total time = 52412.56 ms / 1024 tokens 42.52.443.655 I slot print_timing: id 0 | task 8911 | graphs reused = 7886 42.52.443.655 I slot print_timing: id 0 | task 8911 | graph reallocs = 0 / 0 (same size) / (changed size) 42.52.443.695 I slot release: id 0 | task 8911 | stop processing: n_tokens = 1023, truncated = 0 42.52.443.899 I slot print_timing: id 2 | task 8912 | prompt eval time = 50223.96 ms / 924 tokens ( 54.35 ms per token, 18.40 tokens per second) 42.52.443.906 I slot print_timing: id 2 | task 8912 | eval time = 2184.34 ms / 2 tokens ( 2184.34 ms per token, 0.46 tokens per second) 42.52.443.906 I slot print_timing: id 2 | task 8912 | total time = 52408.30 ms / 926 tokens 42.52.443.906 I slot print_timing: id 2 | task 8912 | graphs reused = 7886 42.52.443.907 I slot print_timing: id 2 | task 8912 | graph reallocs = 0 / 0 (same size) / (changed size) 42.52.443.938 I slot release: id 2 | task 8912 | stop processing: n_tokens = 925, truncated = 0 42.52.444.179 I slot print_timing: id 3 | task 8913 | prompt eval time = 50224.10 ms / 1780 tokens ( 28.22 ms per token, 35.44 tokens per second) 42.52.444.181 I slot print_timing: id 3 | task 8913 | eval time = 2184.41 ms / 2 tokens ( 2184.41 ms per token, 0.46 tokens per second) 42.52.444.182 I slot print_timing: id 3 | task 8913 | total time = 52408.51 ms / 1782 tokens 42.52.444.182 I slot print_timing: id 3 | task 8913 | graphs reused = 7886 42.52.444.182 I slot print_timing: id 3 | task 8913 | graph reallocs = 0 / 0 (same size) / (changed size) 42.52.444.234 I slot release: id 3 | task 8913 | stop processing: n_tokens = 1781, truncated = 0 42.52.444.242 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 421, progress = 0.45, t = 15.96 s / 26.38 tokens per second 42.52.456.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 81368185500 42.52.457.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.587 MiB) 42.56.435.800 I slot launch_slot_: id 0 | task 8923 | processing task, is_child = 0 42.56.435.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.274 MiB) 42.56.462.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.088 MiB) 42.56.498.884 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 81368185743 42.56.498.994 I slot launch_slot_: id 2 | task 8924 | processing task, is_child = 0 42.56.499.070 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 81368186039 42.56.499.163 I slot launch_slot_: id 3 | task 8925 | processing task, is_child = 0 42.56.499.259 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 753, progress = 0.80, t = 15.97 s / 47.15 tokens per second 43.02.707.355 I slot print_timing: id 0 | task 8923 | prompt processing, n_tokens = 118, progress = 0.17, t = 6.21 s / 19.01 tokens per second 43.03.134.534 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 933, progress = 1.00, t = 26.22 s / 35.58 tokens per second 43.03.139.025 I slot print_timing: id 2 | task 8924 | prompt processing, n_tokens = 118, progress = 0.16, t = 6.20 s / 19.02 tokens per second 43.03.143.445 I slot print_timing: id 3 | task 8925 | prompt processing, n_tokens = 140, progress = 0.16, t = 6.20 s / 22.57 tokens per second 43.07.614.806 I slot print_timing: id 0 | task 8923 | prompt processing, n_tokens = 197, progress = 0.28, t = 11.12 s / 17.72 tokens per second 43.07.622.249 I slot print_timing: id 2 | task 8924 | prompt processing, n_tokens = 225, progress = 0.30, t = 11.11 s / 20.25 tokens per second 43.07.626.747 I slot print_timing: id 3 | task 8925 | prompt processing, n_tokens = 268, progress = 0.30, t = 11.11 s / 24.12 tokens per second 43.17.941.306 I slot print_timing: id 1 | task 8918 | prompt eval time = 31128.20 ms / 937 tokens ( 33.22 ms per token, 30.10 tokens per second) 43.17.941.319 I slot print_timing: id 1 | task 8918 | eval time = 10326.51 ms / 2 tokens (10326.51 ms per token, 0.10 tokens per second) 43.17.941.319 I slot print_timing: id 1 | task 8918 | total time = 41454.71 ms / 939 tokens 43.17.941.320 I slot print_timing: id 1 | task 8918 | graphs reused = 7886 43.17.941.320 I slot print_timing: id 1 | task 8918 | graph reallocs = 0 / 0 (same size) / (changed size) 43.17.941.371 I slot release: id 1 | task 8918 | stop processing: n_tokens = 938, truncated = 0 43.17.941.383 I slot print_timing: id 0 | task 8923 | prompt processing, n_tokens = 603, progress = 0.85, t = 21.44 s / 28.12 tokens per second 43.17.947.530 I slot print_timing: id 2 | task 8924 | prompt processing, n_tokens = 603, progress = 0.81, t = 21.44 s / 28.13 tokens per second 43.17.952.315 I slot print_timing: id 3 | task 8925 | prompt processing, n_tokens = 364, progress = 0.41, t = 21.44 s / 16.98 tokens per second 43.22.705.884 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 81393683176 43.22.705.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.462 MiB) 43.25.966.862 I slot launch_slot_: id 1 | task 8930 | processing task, is_child = 0 43.25.966.878 I slot print_timing: id 0 | task 8923 | prompt processing, n_tokens = 709, progress = 0.99, t = 26.21 s / 27.05 tokens per second 43.25.971.616 I slot print_timing: id 2 | task 8924 | prompt processing, n_tokens = 737, progress = 0.99, t = 26.20 s / 28.13 tokens per second 43.25.976.109 I slot print_timing: id 3 | task 8925 | prompt processing, n_tokens = 769, progress = 0.87, t = 26.20 s / 29.35 tokens per second 43.29.283.083 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 118, progress = 0.16, t = 3.31 s / 35.64 tokens per second 43.29.290.719 I slot print_timing: id 3 | task 8925 | prompt processing, n_tokens = 876, progress = 1.00, t = 32.78 s / 26.72 tokens per second 43.30.961.328 I slot print_timing: id 0 | task 8923 | prompt eval time = 32783.66 ms / 713 tokens ( 45.98 ms per token, 21.75 tokens per second) 43.30.961.333 I slot print_timing: id 0 | task 8923 | eval time = 1678.50 ms / 2 tokens ( 1678.50 ms per token, 0.60 tokens per second) 43.30.961.334 I slot print_timing: id 0 | task 8923 | total time = 34462.15 ms / 715 tokens 43.30.961.334 I slot print_timing: id 0 | task 8923 | graphs reused = 7886 43.30.961.335 I slot print_timing: id 0 | task 8923 | graph reallocs = 0 / 0 (same size) / (changed size) 43.30.961.369 I slot release: id 0 | task 8923 | stop processing: n_tokens = 714, truncated = 0 43.30.961.579 I slot print_timing: id 2 | task 8924 | prompt eval time = 32779.39 ms / 741 tokens ( 44.24 ms per token, 22.61 tokens per second) 43.30.961.585 I slot print_timing: id 2 | task 8924 | eval time = 1678.50 ms / 2 tokens ( 1678.50 ms per token, 0.60 tokens per second) 43.30.961.585 I slot print_timing: id 2 | task 8924 | total time = 34457.89 ms / 743 tokens 43.30.961.586 I slot print_timing: id 2 | task 8924 | graphs reused = 7886 43.30.961.586 I slot print_timing: id 2 | task 8924 | graph reallocs = 0 / 0 (same size) / (changed size) 43.30.961.609 I slot release: id 2 | task 8924 | stop processing: n_tokens = 742, truncated = 0 43.30.961.827 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 200, progress = 0.28, t = 4.99 s / 40.08 tokens per second 43.35.736.037 I slot print_timing: id 3 | task 8925 | prompt eval time = 34458.07 ms / 880 tokens ( 39.16 ms per token, 25.54 tokens per second) 43.35.736.040 I slot print_timing: id 3 | task 8925 | eval time = 4774.21 ms / 2 tokens ( 4774.21 ms per token, 0.21 tokens per second) 43.35.736.041 I slot print_timing: id 3 | task 8925 | total time = 39232.29 ms / 882 tokens 43.35.736.041 I slot print_timing: id 3 | task 8925 | graphs reused = 7886 43.35.736.042 I slot print_timing: id 3 | task 8925 | graph reallocs = 0 / 0 (same size) / (changed size) 43.35.736.083 I slot release: id 3 | task 8925 | stop processing: n_tokens = 881, truncated = 0 43.35.736.091 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.884 43.35.736.146 I slot launch_slot_: id 0 | task 8934 | processing task, is_child = 0 43.35.736.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 43.35.756.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 43.35.775.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 43.35.775.306 I slot launch_slot_: id 2 | task 8935 | processing task, is_child = 0 43.35.775.355 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 81411477888 43.35.775.418 I slot launch_slot_: id 3 | task 8936 | processing task, is_child = 0 43.35.782.996 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 603, progress = 0.84, t = 9.76 s / 61.76 tokens per second 43.41.487.272 I slot print_timing: id 0 | task 8934 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.71 s / 19.61 tokens per second 43.41.793.587 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 712, progress = 0.99, t = 15.52 s / 45.89 tokens per second 43.41.798.073 I slot print_timing: id 2 | task 8935 | prompt processing, n_tokens = 118, progress = 0.99, t = 5.70 s / 20.70 tokens per second 43.41.802.535 I slot print_timing: id 3 | task 8936 | prompt processing, n_tokens = 133, progress = 0.15, t = 5.69 s / 23.37 tokens per second 43.43.993.756 I slot print_timing: id 3 | task 8936 | prompt processing, n_tokens = 277, progress = 0.32, t = 8.20 s / 33.79 tokens per second 43.45.339.731 I slot print_timing: id 0 | task 8934 | prompt eval time = 8217.86 ms / 116 tokens ( 70.84 ms per token, 14.12 tokens per second) 43.45.339.736 I slot print_timing: id 0 | task 8934 | eval time = 1346.44 ms / 2 tokens ( 1346.44 ms per token, 0.74 tokens per second) 43.45.339.737 I slot print_timing: id 0 | task 8934 | total time = 9564.30 ms / 118 tokens 43.45.339.737 I slot print_timing: id 0 | task 8934 | graphs reused = 7886 43.45.339.738 I slot print_timing: id 0 | task 8934 | graph reallocs = 0 / 0 (same size) / (changed size) 43.45.339.773 I slot release: id 0 | task 8934 | stop processing: n_tokens = 720, truncated = 0 43.45.340.006 I slot print_timing: id 1 | task 8930 | prompt eval time = 18021.97 ms / 716 tokens ( 25.17 ms per token, 39.73 tokens per second) 43.45.340.011 I slot print_timing: id 1 | task 8930 | eval time = 1346.49 ms / 2 tokens ( 1346.49 ms per token, 0.74 tokens per second) 43.45.340.012 I slot print_timing: id 1 | task 8930 | total time = 19368.45 ms / 718 tokens 43.45.340.012 I slot print_timing: id 1 | task 8930 | graphs reused = 7886 43.45.340.012 I slot print_timing: id 1 | task 8930 | graph reallocs = 0 / 0 (same size) / (changed size) 43.45.340.032 I slot release: id 1 | task 8930 | stop processing: n_tokens = 717, truncated = 0 43.45.340.269 I slot print_timing: id 2 | task 8935 | prompt eval time = 8206.27 ms / 122 tokens ( 67.26 ms per token, 14.87 tokens per second) 43.45.340.272 I slot print_timing: id 2 | task 8935 | eval time = 1346.52 ms / 2 tokens ( 1346.52 ms per token, 0.74 tokens per second) 43.45.340.273 I slot print_timing: id 2 | task 8935 | total time = 9552.80 ms / 124 tokens 43.45.340.273 I slot print_timing: id 2 | task 8935 | graphs reused = 7886 43.45.340.273 I slot print_timing: id 2 | task 8935 | graph reallocs = 0 / 0 (same size) / (changed size) 43.45.340.293 I slot release: id 2 | task 8935 | stop processing: n_tokens = 726, truncated = 0 43.45.340.300 I slot print_timing: id 3 | task 8936 | prompt processing, n_tokens = 360, progress = 0.41, t = 9.54 s / 37.72 tokens per second 43.45.353.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 81421081578 43.45.353.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.403 MiB) 43.50.034.204 I slot launch_slot_: id 0 | task 8941 | processing task, is_child = 0 43.50.034.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 43.50.058.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 43.50.077.956 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 81421081838 43.50.078.055 I slot launch_slot_: id 1 | task 8942 | processing task, is_child = 0 43.50.078.100 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 81421082098 43.50.078.161 I slot launch_slot_: id 2 | task 8943 | processing task, is_child = 0 43.50.078.330 I slot print_timing: id 3 | task 8936 | prompt processing, n_tokens = 766, progress = 0.87, t = 9.56 s / 80.14 tokens per second 43.55.150.646 I slot print_timing: id 0 | task 8941 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.07 s / 27.99 tokens per second 43.56.666.024 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.07 s / 27.99 tokens per second 43.56.670.459 I slot print_timing: id 2 | task 8943 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.07 s / 27.99 tokens per second 43.56.674.872 I slot print_timing: id 3 | task 8936 | prompt processing, n_tokens = 872, progress = 1.00, t = 19.36 s / 45.05 tokens per second 44.03.981.292 I slot print_timing: id 0 | task 8941 | prompt processing, n_tokens = 345, progress = 0.34, t = 13.90 s / 24.81 tokens per second 44.03.981.308 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 345, progress = 0.33, t = 13.90 s / 24.82 tokens per second 44.03.981.316 I slot print_timing: id 2 | task 8943 | prompt processing, n_tokens = 345, progress = 0.35, t = 13.90 s / 24.82 tokens per second 44.09.671.661 I slot print_timing: id 3 | task 8936 | prompt eval time = 28186.26 ms / 876 tokens ( 32.18 ms per token, 31.08 tokens per second) 44.09.671.667 I slot print_timing: id 3 | task 8936 | eval time = 5690.38 ms / 2 tokens ( 5690.38 ms per token, 0.18 tokens per second) 44.09.671.667 I slot print_timing: id 3 | task 8936 | total time = 33876.64 ms / 878 tokens 44.09.671.668 I slot print_timing: id 3 | task 8936 | graphs reused = 7886 44.09.671.668 I slot print_timing: id 3 | task 8936 | graph reallocs = 0 / 0 (same size) / (changed size) 44.09.671.709 I slot release: id 3 | task 8936 | stop processing: n_tokens = 877, truncated = 0 44.09.671.721 I slot print_timing: id 0 | task 8941 | prompt processing, n_tokens = 490, progress = 0.49, t = 19.59 s / 25.01 tokens per second 44.09.677.452 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 518, progress = 0.50, t = 19.59 s / 26.44 tokens per second 44.09.682.253 I slot print_timing: id 2 | task 8943 | prompt processing, n_tokens = 476, progress = 0.48, t = 19.59 s / 24.29 tokens per second 44.22.092.515 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 81445413514 44.22.092.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 44.22.862.906 I slot launch_slot_: id 3 | task 8948 | processing task, is_child = 0 44.22.862.917 I slot print_timing: id 0 | task 8941 | prompt processing, n_tokens = 861, progress = 0.86, t = 32.01 s / 26.89 tokens per second 44.22.867.366 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 861, progress = 0.83, t = 32.01 s / 26.89 tokens per second 44.22.871.789 I slot print_timing: id 2 | task 8943 | prompt processing, n_tokens = 861, progress = 0.87, t = 32.01 s / 26.89 tokens per second 44.29.560.107 I slot print_timing: id 0 | task 8941 | prompt processing, n_tokens = 1002, progress = 1.00, t = 39.48 s / 25.38 tokens per second 44.29.867.001 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 1030, progress = 1.00, t = 39.48 s / 26.09 tokens per second 44.29.871.539 I slot print_timing: id 2 | task 8943 | prompt processing, n_tokens = 988, progress = 1.00, t = 39.48 s / 25.02 tokens per second 44.29.876.064 I slot print_timing: id 3 | task 8948 | prompt processing, n_tokens = 142, progress = 0.14, t = 6.67 s / 21.27 tokens per second 44.32.781.277 I slot print_timing: id 3 | task 8948 | prompt processing, n_tokens = 345, progress = 0.35, t = 9.90 s / 34.87 tokens per second 44.34.816.341 I slot print_timing: id 0 | task 8941 | prompt eval time = 42702.47 ms / 1006 tokens ( 42.45 ms per token, 23.56 tokens per second) 44.34.816.344 I slot print_timing: id 0 | task 8941 | eval time = 2035.69 ms / 2 tokens ( 2035.69 ms per token, 0.49 tokens per second) 44.34.816.345 I slot print_timing: id 0 | task 8941 | total time = 44738.17 ms / 1008 tokens 44.34.816.346 I slot print_timing: id 0 | task 8941 | graphs reused = 7886 44.34.816.346 I slot print_timing: id 0 | task 8941 | graph reallocs = 0 / 0 (same size) / (changed size) 44.34.816.386 I slot release: id 0 | task 8941 | stop processing: n_tokens = 1007, truncated = 0 44.34.816.592 I slot print_timing: id 1 | task 8942 | prompt eval time = 42702.63 ms / 1034 tokens ( 41.30 ms per token, 24.21 tokens per second) 44.34.816.595 I slot print_timing: id 1 | task 8942 | eval time = 2035.73 ms / 2 tokens ( 2035.73 ms per token, 0.49 tokens per second) 44.34.816.595 I slot print_timing: id 1 | task 8942 | total time = 44738.36 ms / 1036 tokens 44.34.816.595 I slot print_timing: id 1 | task 8942 | graphs reused = 7886 44.34.816.596 I slot print_timing: id 1 | task 8942 | graph reallocs = 0 / 0 (same size) / (changed size) 44.34.816.624 I slot release: id 1 | task 8942 | stop processing: n_tokens = 1035, truncated = 0 44.34.816.870 I slot print_timing: id 2 | task 8943 | prompt eval time = 42702.98 ms / 992 tokens ( 43.05 ms per token, 23.23 tokens per second) 44.34.816.873 I slot print_timing: id 2 | task 8943 | eval time = 2035.61 ms / 2 tokens ( 2035.61 ms per token, 0.49 tokens per second) 44.34.816.873 I slot print_timing: id 2 | task 8943 | total time = 44738.59 ms / 994 tokens 44.34.816.874 I slot print_timing: id 2 | task 8943 | graphs reused = 7886 44.34.816.874 I slot print_timing: id 2 | task 8943 | graph reallocs = 0 / 0 (same size) / (changed size) 44.34.816.899 I slot release: id 2 | task 8943 | stop processing: n_tokens = 993, truncated = 0 44.34.816.906 I slot print_timing: id 3 | task 8948 | prompt processing, n_tokens = 483, progress = 0.48, t = 11.93 s / 40.48 tokens per second 44.34.837.975 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.883 44.34.838.015 I slot launch_slot_: id 0 | task 8953 | processing task, is_child = 0 44.34.838.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.092 MiB) 44.39.159.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.965 MiB) 44.39.185.593 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 81470558430 44.39.185.715 I slot launch_slot_: id 1 | task 8954 | processing task, is_child = 0 44.39.185.766 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 81470558704 44.39.185.836 I slot launch_slot_: id 2 | task 8955 | processing task, is_child = 0 44.39.193.552 I slot print_timing: id 3 | task 8948 | prompt processing, n_tokens = 861, progress = 0.86, t = 11.95 s / 72.03 tokens per second 44.46.182.487 I slot print_timing: id 0 | task 8953 | prompt processing, n_tokens = 128, progress = 1.00, t = 7.00 s / 18.29 tokens per second 44.46.617.086 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 193, progress = 0.22, t = 6.99 s / 27.61 tokens per second 44.46.621.625 I slot print_timing: id 2 | task 8955 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.99 s / 16.45 tokens per second 44.46.626.068 I slot print_timing: id 3 | task 8948 | prompt processing, n_tokens = 995, progress = 1.00, t = 23.30 s / 42.71 tokens per second 44.51.017.674 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 327, progress = 0.37, t = 11.82 s / 27.66 tokens per second 44.51.017.685 I slot print_timing: id 2 | task 8955 | prompt processing, n_tokens = 293, progress = 0.29, t = 11.82 s / 24.78 tokens per second 44.54.634.038 I slot print_timing: id 0 | task 8953 | prompt eval time = 11831.59 ms / 132 tokens ( 89.63 ms per token, 11.16 tokens per second) 44.54.634.042 I slot print_timing: id 0 | task 8953 | eval time = 3616.60 ms / 2 tokens ( 3616.60 ms per token, 0.28 tokens per second) 44.54.634.042 I slot print_timing: id 0 | task 8953 | total time = 15448.19 ms / 134 tokens 44.54.634.043 I slot print_timing: id 0 | task 8953 | graphs reused = 7886 44.54.634.043 I slot print_timing: id 0 | task 8953 | graph reallocs = 0 / 0 (same size) / (changed size) 44.54.634.085 I slot release: id 0 | task 8953 | stop processing: n_tokens = 994, truncated = 0 44.54.634.285 I slot print_timing: id 3 | task 8948 | prompt eval time = 28132.45 ms / 999 tokens ( 28.16 ms per token, 35.51 tokens per second) 44.54.634.287 I slot print_timing: id 3 | task 8948 | eval time = 3616.63 ms / 2 tokens ( 3616.63 ms per token, 0.28 tokens per second) 44.54.634.288 I slot print_timing: id 3 | task 8948 | total time = 31749.08 ms / 1001 tokens 44.54.634.288 I slot print_timing: id 3 | task 8948 | graphs reused = 7886 44.54.634.288 I slot print_timing: id 3 | task 8948 | graph reallocs = 0 / 0 (same size) / (changed size) 44.54.634.321 I slot release: id 3 | task 8948 | stop processing: n_tokens = 1000, truncated = 0 44.54.634.329 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 363, progress = 0.41, t = 15.44 s / 23.51 tokens per second 44.54.640.658 I slot print_timing: id 2 | task 8955 | prompt processing, n_tokens = 502, progress = 0.49, t = 15.44 s / 32.51 tokens per second 45.00.793.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 81490375890 45.00.793.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.484 MiB) 45.01.934.688 I slot launch_slot_: id 0 | task 8960 | processing task, is_child = 0 45.01.934.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.777 MiB) 45.01.953.594 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 81490376126 45.01.953.693 I slot launch_slot_: id 3 | task 8961 | processing task, is_child = 0 45.01.953.787 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 730, progress = 0.83, t = 21.60 s / 33.80 tokens per second 45.01.958.179 I slot print_timing: id 2 | task 8955 | prompt processing, n_tokens = 773, progress = 0.76, t = 21.60 s / 35.79 tokens per second 45.08.172.165 I slot print_timing: id 0 | task 8960 | prompt processing, n_tokens = 115, progress = 0.13, t = 6.22 s / 18.49 tokens per second 45.09.318.542 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 875, progress = 1.00, t = 28.98 s / 30.19 tokens per second 45.09.323.047 I slot print_timing: id 2 | task 8955 | prompt processing, n_tokens = 1014, progress = 1.00, t = 28.98 s / 34.99 tokens per second 45.09.327.549 I slot print_timing: id 3 | task 8961 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.21 s / 18.52 tokens per second 45.14.042.416 I slot print_timing: id 0 | task 8960 | prompt processing, n_tokens = 293, progress = 0.33, t = 12.09 s / 24.24 tokens per second 45.14.042.427 I slot print_timing: id 3 | task 8961 | prompt processing, n_tokens = 293, progress = 0.29, t = 12.08 s / 24.26 tokens per second 45.17.917.066 I slot print_timing: id 1 | task 8954 | prompt eval time = 34848.80 ms / 879 tokens ( 39.65 ms per token, 25.22 tokens per second) 45.17.917.068 I slot print_timing: id 1 | task 8954 | eval time = 3874.84 ms / 2 tokens ( 3874.84 ms per token, 0.26 tokens per second) 45.17.917.069 I slot print_timing: id 1 | task 8954 | total time = 38723.64 ms / 881 tokens 45.17.917.069 I slot print_timing: id 1 | task 8954 | graphs reused = 7886 45.17.917.070 I slot print_timing: id 1 | task 8954 | graph reallocs = 0 / 0 (same size) / (changed size) 45.17.917.111 I slot release: id 1 | task 8954 | stop processing: n_tokens = 880, truncated = 0 45.17.917.263 I slot print_timing: id 2 | task 8955 | prompt eval time = 34848.92 ms / 1018 tokens ( 34.23 ms per token, 29.21 tokens per second) 45.17.917.265 I slot print_timing: id 2 | task 8955 | eval time = 3874.86 ms / 2 tokens ( 3874.86 ms per token, 0.26 tokens per second) 45.17.917.266 I slot print_timing: id 2 | task 8955 | total time = 38723.77 ms / 1020 tokens 45.17.917.266 I slot print_timing: id 2 | task 8955 | graphs reused = 7886 45.17.917.266 I slot print_timing: id 2 | task 8955 | graph reallocs = 0 / 0 (same size) / (changed size) 45.17.917.301 I slot release: id 2 | task 8955 | stop processing: n_tokens = 1019, truncated = 0 45.17.917.309 I slot print_timing: id 0 | task 8960 | prompt processing, n_tokens = 380, progress = 0.42, t = 15.96 s / 23.80 tokens per second 45.17.924.217 I slot print_timing: id 3 | task 8961 | prompt processing, n_tokens = 493, progress = 0.49, t = 15.95 s / 30.90 tokens per second 45.22.601.982 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.813 (> 0.100 thold), f_keep = 0.786 45.22.602.050 I slot launch_slot_: id 2 | task 8966 | processing task, is_child = 0 45.22.602.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.523 MiB) 45.25.870.815 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 81513658916 45.25.870.931 I slot launch_slot_: id 1 | task 8967 | processing task, is_child = 0 45.25.870.938 I slot print_timing: id 0 | task 8960 | prompt processing, n_tokens = 773, progress = 0.86, t = 20.65 s / 37.44 tokens per second 45.25.883.324 I slot print_timing: id 3 | task 8961 | prompt processing, n_tokens = 773, progress = 0.77, t = 20.64 s / 37.45 tokens per second 45.33.701.266 I slot print_timing: id 0 | task 8960 | prompt processing, n_tokens = 892, progress = 1.00, t = 31.75 s / 28.10 tokens per second 45.34.132.346 I slot print_timing: id 1 | task 8967 | prompt processing, n_tokens = 115, progress = 0.13, t = 7.83 s / 14.69 tokens per second 45.34.136.767 I slot print_timing: id 2 | task 8966 | prompt processing, n_tokens = 208, progress = 1.00, t = 7.83 s / 26.58 tokens per second 45.34.141.304 I slot print_timing: id 3 | task 8961 | prompt processing, n_tokens = 1005, progress = 1.00, t = 31.74 s / 31.67 tokens per second 45.36.684.378 I slot print_timing: id 1 | task 8967 | prompt processing, n_tokens = 293, progress = 0.32, t = 10.81 s / 27.11 tokens per second 45.38.190.767 I slot print_timing: id 0 | task 8960 | prompt eval time = 34730.28 ms / 896 tokens ( 38.76 ms per token, 25.80 tokens per second) 45.38.190.769 I slot print_timing: id 0 | task 8960 | eval time = 1506.78 ms / 2 tokens ( 1506.78 ms per token, 0.66 tokens per second) 45.38.190.770 I slot print_timing: id 0 | task 8960 | total time = 36237.06 ms / 898 tokens 45.38.190.770 I slot print_timing: id 0 | task 8960 | graphs reused = 7886 45.38.190.771 I slot print_timing: id 0 | task 8960 | graph reallocs = 0 / 0 (same size) / (changed size) 45.38.190.814 I slot release: id 0 | task 8960 | stop processing: n_tokens = 897, truncated = 0 45.38.190.965 I slot print_timing: id 2 | task 8966 | prompt eval time = 10808.71 ms / 212 tokens ( 50.98 ms per token, 19.61 tokens per second) 45.38.190.967 I slot print_timing: id 2 | task 8966 | eval time = 1506.81 ms / 2 tokens ( 1506.81 ms per token, 0.66 tokens per second) 45.38.190.968 I slot print_timing: id 2 | task 8966 | total time = 12315.52 ms / 214 tokens 45.38.190.968 I slot print_timing: id 2 | task 8966 | graphs reused = 7886 45.38.190.968 I slot print_timing: id 2 | task 8966 | graph reallocs = 0 / 0 (same size) / (changed size) 45.38.191.000 I slot release: id 2 | task 8966 | stop processing: n_tokens = 986, truncated = 0 45.38.191.182 I slot print_timing: id 3 | task 8961 | prompt eval time = 34721.55 ms / 1009 tokens ( 34.41 ms per token, 29.06 tokens per second) 45.38.191.184 I slot print_timing: id 3 | task 8961 | eval time = 1506.81 ms / 2 tokens ( 1506.81 ms per token, 0.66 tokens per second) 45.38.191.184 I slot print_timing: id 3 | task 8961 | total time = 36228.36 ms / 1011 tokens 45.38.191.185 I slot print_timing: id 3 | task 8961 | graphs reused = 7886 45.38.191.185 I slot print_timing: id 3 | task 8961 | graph reallocs = 0 / 0 (same size) / (changed size) 45.38.191.211 I slot release: id 3 | task 8961 | stop processing: n_tokens = 1010, truncated = 0 45.38.191.218 I slot print_timing: id 1 | task 8967 | prompt processing, n_tokens = 386, progress = 0.43, t = 12.32 s / 31.34 tokens per second 45.38.204.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 45.38.204.112 I slot launch_slot_: id 0 | task 8972 | processing task, is_child = 0 45.38.204.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 45.42.873.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 45.42.892.412 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 81533932805 45.42.892.538 I slot launch_slot_: id 2 | task 8973 | processing task, is_child = 0 45.42.892.589 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 81533933016 45.42.892.677 I slot launch_slot_: id 3 | task 8974 | processing task, is_child = 0 45.42.900.302 I slot print_timing: id 1 | task 8967 | prompt processing, n_tokens = 773, progress = 0.86, t = 12.33 s / 62.70 tokens per second 45.48.384.715 I slot print_timing: id 0 | task 8972 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.49 s / 18.94 tokens per second 45.48.680.768 I slot print_timing: id 1 | task 8967 | prompt processing, n_tokens = 898, progress = 1.00, t = 22.51 s / 39.89 tokens per second 45.48.685.473 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 116, progress = 0.13, t = 5.48 s / 21.17 tokens per second 45.48.690.087 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 116, progress = 0.12, t = 5.48 s / 21.17 tokens per second 45.51.606.016 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 232, progress = 0.26, t = 8.70 s / 26.66 tokens per second 45.51.606.027 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 232, progress = 0.24, t = 8.70 s / 26.66 tokens per second 45.56.187.090 I slot print_timing: id 0 | task 8972 | prompt eval time = 8713.10 ms / 108 tokens ( 80.68 ms per token, 12.40 tokens per second) 45.56.187.095 I slot print_timing: id 0 | task 8972 | eval time = 4581.30 ms / 2 tokens ( 4581.30 ms per token, 0.22 tokens per second) 45.56.187.095 I slot print_timing: id 0 | task 8972 | total time = 13294.40 ms / 110 tokens 45.56.187.096 I slot print_timing: id 0 | task 8972 | graphs reused = 7886 45.56.187.096 I slot print_timing: id 0 | task 8972 | graph reallocs = 0 / 0 (same size) / (changed size) 45.56.187.134 I slot release: id 0 | task 8972 | stop processing: n_tokens = 882, truncated = 0 45.56.187.363 I slot print_timing: id 1 | task 8967 | prompt eval time = 25730.64 ms / 902 tokens ( 28.53 ms per token, 35.06 tokens per second) 45.56.187.372 I slot print_timing: id 1 | task 8967 | eval time = 4581.35 ms / 2 tokens ( 4581.35 ms per token, 0.22 tokens per second) 45.56.187.372 I slot print_timing: id 1 | task 8967 | total time = 30312.00 ms / 904 tokens 45.56.187.372 I slot print_timing: id 1 | task 8967 | graphs reused = 7886 45.56.187.373 I slot print_timing: id 1 | task 8967 | graph reallocs = 0 / 0 (same size) / (changed size) 45.56.187.404 I slot release: id 1 | task 8967 | stop processing: n_tokens = 903, truncated = 0 45.56.187.413 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 390, progress = 0.43, t = 13.28 s / 29.36 tokens per second 45.56.193.280 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 436, progress = 0.46, t = 13.28 s / 32.83 tokens per second 46.04.079.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 81551928939 46.04.079.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 46.04.851.934 I slot launch_slot_: id 0 | task 8979 | processing task, is_child = 0 46.04.851.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 46.04.883.470 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 81551929209 46.04.883.577 I slot launch_slot_: id 1 | task 8980 | processing task, is_child = 0 46.04.883.732 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 774, progress = 0.85, t = 21.17 s / 36.55 tokens per second 46.04.888.195 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 774, progress = 0.81, t = 21.17 s / 36.55 tokens per second 46.11.853.543 I slot print_timing: id 0 | task 8979 | prompt processing, n_tokens = 116, progress = 0.12, t = 6.97 s / 16.64 tokens per second 46.12.623.955 I slot print_timing: id 1 | task 8980 | prompt processing, n_tokens = 176, progress = 0.13, t = 6.97 s / 25.25 tokens per second 46.12.628.361 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 902, progress = 1.00, t = 28.95 s / 31.16 tokens per second 46.12.632.982 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 948, progress = 1.00, t = 28.95 s / 32.75 tokens per second 46.17.372.780 I slot print_timing: id 0 | task 8979 | prompt processing, n_tokens = 232, progress = 0.25, t = 12.49 s / 18.58 tokens per second 46.17.372.793 I slot print_timing: id 1 | task 8980 | prompt processing, n_tokens = 431, progress = 0.32, t = 12.49 s / 34.51 tokens per second 46.24.396.689 I slot print_timing: id 2 | task 8973 | prompt eval time = 34467.82 ms / 906 tokens ( 38.04 ms per token, 26.29 tokens per second) 46.24.396.692 I slot print_timing: id 2 | task 8973 | eval time = 7024.14 ms / 2 tokens ( 7024.14 ms per token, 0.14 tokens per second) 46.24.396.693 I slot print_timing: id 2 | task 8973 | total time = 41491.96 ms / 908 tokens 46.24.396.694 I slot print_timing: id 2 | task 8973 | graphs reused = 7886 46.24.396.694 I slot print_timing: id 2 | task 8973 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.396.734 I slot release: id 2 | task 8973 | stop processing: n_tokens = 907, truncated = 0 46.24.396.958 I slot print_timing: id 3 | task 8974 | prompt eval time = 34467.97 ms / 952 tokens ( 36.21 ms per token, 27.62 tokens per second) 46.24.396.961 I slot print_timing: id 3 | task 8974 | eval time = 7024.19 ms / 2 tokens ( 7024.19 ms per token, 0.14 tokens per second) 46.24.396.961 I slot print_timing: id 3 | task 8974 | total time = 41492.16 ms / 954 tokens 46.24.396.962 I slot print_timing: id 3 | task 8974 | graphs reused = 7886 46.24.396.962 I slot print_timing: id 3 | task 8974 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.396.988 I slot release: id 3 | task 8974 | stop processing: n_tokens = 953, truncated = 0 46.24.396.997 I slot print_timing: id 0 | task 8979 | prompt processing, n_tokens = 424, progress = 0.45, t = 19.51 s / 21.73 tokens per second 46.24.403.659 I slot print_timing: id 1 | task 8980 | prompt processing, n_tokens = 840, progress = 0.62, t = 19.51 s / 43.05 tokens per second 46.31.604.963 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 81580138539 46.31.605.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.964 MiB) 46.32.367.348 I slot launch_slot_: id 2 | task 8985 | processing task, is_child = 0 46.32.367.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.842 MiB) 46.32.387.114 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 81580138793 46.32.387.217 I slot launch_slot_: id 3 | task 8986 | processing task, is_child = 0 46.32.387.226 I slot print_timing: id 0 | task 8979 | prompt processing, n_tokens = 774, progress = 0.82, t = 26.72 s / 28.97 tokens per second 46.32.391.682 I slot print_timing: id 1 | task 8980 | prompt processing, n_tokens = 1152, progress = 0.85, t = 26.72 s / 43.11 tokens per second 46.40.798.479 I slot print_timing: id 0 | task 8979 | prompt processing, n_tokens = 936, progress = 1.00, t = 35.91 s / 26.06 tokens per second 46.41.230.524 I slot print_timing: id 1 | task 8980 | prompt processing, n_tokens = 1352, progress = 1.00, t = 35.91 s / 37.64 tokens per second 46.41.235.051 I slot print_timing: id 2 | task 8985 | prompt processing, n_tokens = 176, progress = 0.13, t = 8.40 s / 20.95 tokens per second 46.41.239.474 I slot print_timing: id 3 | task 8986 | prompt processing, n_tokens = 176, progress = 0.14, t = 8.40 s / 20.95 tokens per second 46.47.349.807 I slot print_timing: id 2 | task 8985 | prompt processing, n_tokens = 431, progress = 0.32, t = 14.95 s / 28.82 tokens per second 46.47.349.825 I slot print_timing: id 3 | task 8986 | prompt processing, n_tokens = 431, progress = 0.34, t = 14.95 s / 28.82 tokens per second 46.55.876.952 I slot print_timing: id 0 | task 8979 | prompt eval time = 42465.98 ms / 940 tokens ( 45.18 ms per token, 22.14 tokens per second) 46.55.876.957 I slot print_timing: id 0 | task 8979 | eval time = 8527.38 ms / 2 tokens ( 8527.38 ms per token, 0.12 tokens per second) 46.55.876.957 I slot print_timing: id 0 | task 8979 | total time = 50993.36 ms / 942 tokens 46.55.876.958 I slot print_timing: id 0 | task 8979 | graphs reused = 7886 46.55.876.958 I slot print_timing: id 0 | task 8979 | graph reallocs = 0 / 0 (same size) / (changed size) 46.55.877.006 I slot release: id 0 | task 8979 | stop processing: n_tokens = 941, truncated = 0 46.55.877.229 I slot print_timing: id 1 | task 8980 | prompt eval time = 42466.14 ms / 1356 tokens ( 31.32 ms per token, 31.93 tokens per second) 46.55.877.232 I slot print_timing: id 1 | task 8980 | eval time = 8527.43 ms / 2 tokens ( 8527.43 ms per token, 0.12 tokens per second) 46.55.877.232 I slot print_timing: id 1 | task 8980 | total time = 50993.57 ms / 1358 tokens 46.55.877.232 I slot print_timing: id 1 | task 8980 | graphs reused = 7886 46.55.877.233 I slot print_timing: id 1 | task 8980 | graph reallocs = 0 / 0 (same size) / (changed size) 46.55.877.279 I slot release: id 1 | task 8980 | stop processing: n_tokens = 1357, truncated = 0 46.55.877.289 I slot print_timing: id 2 | task 8985 | prompt processing, n_tokens = 826, progress = 0.62, t = 23.48 s / 35.18 tokens per second 46.55.883.741 I slot print_timing: id 3 | task 8986 | prompt processing, n_tokens = 743, progress = 0.59, t = 23.48 s / 31.64 tokens per second 47.03.475.100 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 47.03.475.186 I slot launch_slot_: id 1 | task 8991 | processing task, is_child = 0 47.03.475.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.216 MiB) 47.04.624.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 81611618811 47.04.624.362 I slot launch_slot_: id 0 | task 8992 | processing task, is_child = 0 47.04.632.031 I slot print_timing: id 2 | task 8985 | prompt processing, n_tokens = 1152, progress = 0.86, t = 31.08 s / 37.07 tokens per second 47.04.636.499 I slot print_timing: id 3 | task 8986 | prompt processing, n_tokens = 1152, progress = 0.92, t = 31.08 s / 37.07 tokens per second 47.11.260.971 I slot print_timing: id 0 | task 8992 | prompt processing, n_tokens = 139, progress = 0.18, t = 6.64 s / 20.94 tokens per second 47.12.033.066 I slot print_timing: id 1 | task 8991 | prompt processing, n_tokens = 144, progress = 1.00, t = 6.64 s / 21.70 tokens per second 47.12.037.606 I slot print_timing: id 2 | task 8985 | prompt processing, n_tokens = 1338, progress = 1.00, t = 38.86 s / 34.43 tokens per second 47.12.042.119 I slot print_timing: id 3 | task 8986 | prompt processing, n_tokens = 1255, progress = 1.00, t = 38.86 s / 32.29 tokens per second 47.14.229.349 I slot print_timing: id 0 | task 8992 | prompt processing, n_tokens = 276, progress = 0.35, t = 9.60 s / 28.74 tokens per second 47.19.106.969 I slot print_timing: id 1 | task 8991 | prompt eval time = 9604.43 ms / 148 tokens ( 64.89 ms per token, 15.41 tokens per second) 47.19.106.972 I slot print_timing: id 1 | task 8991 | eval time = 4878.08 ms / 2 tokens ( 4878.08 ms per token, 0.20 tokens per second) 47.19.106.973 I slot print_timing: id 1 | task 8991 | total time = 14482.51 ms / 150 tokens 47.19.106.974 I slot print_timing: id 1 | task 8991 | graphs reused = 7886 47.19.106.974 I slot print_timing: id 1 | task 8991 | graph reallocs = 0 / 0 (same size) / (changed size) 47.19.107.025 I slot release: id 1 | task 8991 | stop processing: n_tokens = 1301, truncated = 0 47.19.107.224 I slot print_timing: id 2 | task 8985 | prompt eval time = 41833.02 ms / 1342 tokens ( 31.17 ms per token, 32.08 tokens per second) 47.19.107.226 I slot print_timing: id 2 | task 8985 | eval time = 4878.11 ms / 2 tokens ( 4878.11 ms per token, 0.20 tokens per second) 47.19.107.227 I slot print_timing: id 2 | task 8985 | total time = 46711.13 ms / 1344 tokens 47.19.107.227 I slot print_timing: id 2 | task 8985 | graphs reused = 7886 47.19.107.228 I slot print_timing: id 2 | task 8985 | graph reallocs = 0 / 0 (same size) / (changed size) 47.19.107.268 I slot release: id 2 | task 8985 | stop processing: n_tokens = 1343, truncated = 0 47.19.107.504 I slot print_timing: id 3 | task 8986 | prompt eval time = 41833.16 ms / 1259 tokens ( 33.23 ms per token, 30.10 tokens per second) 47.19.107.506 I slot print_timing: id 3 | task 8986 | eval time = 4878.16 ms / 2 tokens ( 4878.16 ms per token, 0.20 tokens per second) 47.19.107.507 I slot print_timing: id 3 | task 8986 | total time = 46711.32 ms / 1261 tokens 47.19.107.507 I slot print_timing: id 3 | task 8986 | graphs reused = 7886 47.19.107.507 I slot print_timing: id 3 | task 8986 | graph reallocs = 0 / 0 (same size) / (changed size) 47.19.107.536 I slot release: id 3 | task 8986 | stop processing: n_tokens = 1260, truncated = 0 47.19.107.544 I slot print_timing: id 0 | task 8992 | prompt processing, n_tokens = 681, progress = 0.86, t = 14.48 s / 47.02 tokens per second 47.19.117.909 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 81634848830 47.19.117.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.279 MiB) 47.20.593.755 I slot launch_slot_: id 1 | task 8997 | processing task, is_child = 0 47.20.593.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.654 MiB) 47.20.613.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.151 MiB) 47.20.646.502 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 81634849073 47.20.646.623 I slot launch_slot_: id 2 | task 8998 | processing task, is_child = 0 47.20.646.681 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 81634849341 47.20.646.762 I slot launch_slot_: id 3 | task 8999 | processing task, is_child = 0 47.20.646.769 I slot print_timing: id 0 | task 8992 | prompt processing, n_tokens = 788, progress = 0.99, t = 14.49 s / 54.37 tokens per second 47.26.148.828 I slot print_timing: id 1 | task 8997 | prompt processing, n_tokens = 139, progress = 0.17, t = 5.50 s / 25.28 tokens per second 47.26.154.741 I slot print_timing: id 2 | task 8998 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.50 s / 27.10 tokens per second 47.26.159.151 I slot print_timing: id 3 | task 8999 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.50 s / 27.10 tokens per second 47.31.377.657 I slot print_timing: id 0 | task 8992 | prompt eval time = 21524.45 ms / 792 tokens ( 27.18 ms per token, 36.80 tokens per second) 47.31.377.661 I slot print_timing: id 0 | task 8992 | eval time = 5228.84 ms / 2 tokens ( 5228.84 ms per token, 0.19 tokens per second) 47.31.377.662 I slot print_timing: id 0 | task 8992 | total time = 26753.28 ms / 794 tokens 47.31.377.662 I slot print_timing: id 0 | task 8992 | graphs reused = 7886 47.31.377.662 I slot print_timing: id 0 | task 8992 | graph reallocs = 0 / 0 (same size) / (changed size) 47.31.377.702 I slot release: id 0 | task 8992 | stop processing: n_tokens = 793, truncated = 0 47.31.377.715 I slot print_timing: id 1 | task 8997 | prompt processing, n_tokens = 287, progress = 0.36, t = 10.73 s / 26.76 tokens per second 47.31.377.723 I slot print_timing: id 2 | task 8998 | prompt processing, n_tokens = 285, progress = 0.32, t = 10.73 s / 26.57 tokens per second 47.31.377.729 I slot print_timing: id 3 | task 8999 | prompt processing, n_tokens = 285, progress = 0.33, t = 10.73 s / 26.57 tokens per second 47.33.179.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 81647119507 47.33.179.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.779 MiB) 47.33.611.027 I slot launch_slot_: id 0 | task 9003 | processing task, is_child = 0 47.33.611.114 I slot print_timing: id 1 | task 8997 | prompt processing, n_tokens = 292, progress = 0.36, t = 12.53 s / 23.31 tokens per second 47.33.615.730 I slot print_timing: id 2 | task 8998 | prompt processing, n_tokens = 375, progress = 0.42, t = 12.53 s / 29.93 tokens per second 47.33.620.140 I slot print_timing: id 3 | task 8999 | prompt processing, n_tokens = 343, progress = 0.40, t = 12.53 s / 27.38 tokens per second 47.48.986.565 I slot print_timing: id 0 | task 9003 | prompt processing, n_tokens = 163, progress = 0.21, t = 15.38 s / 10.60 tokens per second 47.49.421.213 I slot print_timing: id 1 | task 8997 | prompt processing, n_tokens = 681, progress = 0.84, t = 28.34 s / 24.03 tokens per second 47.49.425.612 I slot print_timing: id 2 | task 8998 | prompt processing, n_tokens = 741, progress = 0.83, t = 28.34 s / 26.15 tokens per second 47.49.430.040 I slot print_timing: id 3 | task 8999 | prompt processing, n_tokens = 741, progress = 0.86, t = 28.34 s / 26.15 tokens per second 47.55.296.873 I slot print_timing: id 0 | task 9003 | prompt processing, n_tokens = 274, progress = 0.35, t = 21.69 s / 12.63 tokens per second 47.55.729.086 I slot print_timing: id 1 | task 8997 | prompt processing, n_tokens = 804, progress = 1.00, t = 34.65 s / 23.21 tokens per second 47.55.734.169 I slot print_timing: id 2 | task 8998 | prompt processing, n_tokens = 887, progress = 1.00, t = 34.65 s / 25.60 tokens per second 47.55.738.717 I slot print_timing: id 3 | task 8999 | prompt processing, n_tokens = 855, progress = 1.00, t = 34.65 s / 24.68 tokens per second 48.00.412.076 I slot print_timing: id 0 | task 9003 | prompt processing, n_tokens = 655, progress = 0.83, t = 26.80 s / 24.44 tokens per second 48.02.440.073 I slot print_timing: id 1 | task 8997 | prompt eval time = 39760.39 ms / 808 tokens ( 49.21 ms per token, 20.32 tokens per second) 48.02.440.076 I slot print_timing: id 1 | task 8997 | eval time = 2028.44 ms / 2 tokens ( 2028.44 ms per token, 0.49 tokens per second) 48.02.440.077 I slot print_timing: id 1 | task 8997 | total time = 41788.82 ms / 810 tokens 48.02.440.077 I slot print_timing: id 1 | task 8997 | graphs reused = 7886 48.02.440.078 I slot print_timing: id 1 | task 8997 | graph reallocs = 0 / 0 (same size) / (changed size) 48.02.440.119 I slot release: id 1 | task 8997 | stop processing: n_tokens = 809, truncated = 0 48.02.440.310 I slot print_timing: id 2 | task 8998 | prompt eval time = 39760.50 ms / 891 tokens ( 44.62 ms per token, 22.41 tokens per second) 48.02.440.316 I slot print_timing: id 2 | task 8998 | eval time = 2028.47 ms / 2 tokens ( 2028.47 ms per token, 0.49 tokens per second) 48.02.440.317 I slot print_timing: id 2 | task 8998 | total time = 41788.97 ms / 893 tokens 48.02.440.317 I slot print_timing: id 2 | task 8998 | graphs reused = 7886 48.02.440.317 I slot print_timing: id 2 | task 8998 | graph reallocs = 0 / 0 (same size) / (changed size) 48.02.440.346 I slot release: id 2 | task 8998 | stop processing: n_tokens = 892, truncated = 0 48.02.440.595 I slot print_timing: id 3 | task 8999 | prompt eval time = 39760.63 ms / 859 tokens ( 46.29 ms per token, 21.60 tokens per second) 48.02.440.596 I slot print_timing: id 3 | task 8999 | eval time = 2028.53 ms / 2 tokens ( 2028.53 ms per token, 0.49 tokens per second) 48.02.440.596 I slot print_timing: id 3 | task 8999 | total time = 41789.16 ms / 861 tokens 48.02.440.597 I slot print_timing: id 3 | task 8999 | graphs reused = 7886 48.02.440.597 I slot print_timing: id 3 | task 8999 | graph reallocs = 0 / 0 (same size) / (changed size) 48.02.440.617 I slot release: id 3 | task 8999 | stop processing: n_tokens = 860, truncated = 0 48.02.440.624 I slot print_timing: id 0 | task 9003 | prompt processing, n_tokens = 786, progress = 0.99, t = 28.83 s / 27.26 tokens per second 48.02.629.018 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 81678181924 48.02.629.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.279 MiB) 48.02.648.283 I slot launch_slot_: id 1 | task 9009 | processing task, is_child = 0 48.02.648.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.276 MiB) 48.02.666.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 48.02.685.332 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 81678182151 48.02.685.438 I slot launch_slot_: id 2 | task 9010 | processing task, is_child = 0 48.02.685.484 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 81678182422 48.02.685.559 I slot launch_slot_: id 3 | task 9011 | processing task, is_child = 0 48.08.650.410 I slot print_timing: id 0 | task 9003 | prompt eval time = 29017.97 ms / 790 tokens ( 36.73 ms per token, 27.22 tokens per second) 48.08.650.412 I slot print_timing: id 0 | task 9003 | eval time = 6021.40 ms / 2 tokens ( 6021.40 ms per token, 0.17 tokens per second) 48.08.650.413 I slot print_timing: id 0 | task 9003 | total time = 35039.37 ms / 792 tokens 48.08.650.413 I slot print_timing: id 0 | task 9003 | graphs reused = 7886 48.08.650.413 I slot print_timing: id 0 | task 9003 | graph reallocs = 0 / 0 (same size) / (changed size) 48.08.650.448 I slot release: id 0 | task 9003 | stop processing: n_tokens = 791, truncated = 0 48.08.650.459 I slot print_timing: id 1 | task 9009 | prompt processing, n_tokens = 163, progress = 0.19, t = 5.96 s / 27.33 tokens per second 48.08.655.607 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 163, progress = 0.21, t = 5.96 s / 27.33 tokens per second 48.08.660.695 I slot print_timing: id 3 | task 9011 | prompt processing, n_tokens = 163, progress = 0.21, t = 5.96 s / 27.33 tokens per second 48.12.129.678 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 48.12.129.753 I slot launch_slot_: id 0 | task 9014 | processing task, is_child = 0 48.12.565.003 I slot print_timing: id 1 | task 9009 | prompt processing, n_tokens = 287, progress = 0.34, t = 9.44 s / 30.39 tokens per second 48.12.565.015 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 262, progress = 0.34, t = 9.44 s / 27.74 tokens per second 48.12.569.479 I slot print_timing: id 3 | task 9011 | prompt processing, n_tokens = 258, progress = 0.33, t = 9.44 s / 27.32 tokens per second 48.24.169.832 I slot print_timing: id 0 | task 9014 | prompt processing, n_tokens = 143, progress = 1.00, t = 12.04 s / 11.88 tokens per second 48.24.346.688 I slot print_timing: id 1 | task 9009 | prompt processing, n_tokens = 339, progress = 0.40, t = 21.48 s / 15.78 tokens per second 48.24.351.332 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 655, progress = 0.84, t = 21.48 s / 30.49 tokens per second 48.24.355.745 I slot print_timing: id 3 | task 9011 | prompt processing, n_tokens = 655, progress = 0.85, t = 21.48 s / 30.49 tokens per second 48.31.458.740 I slot print_timing: id 1 | task 9009 | prompt processing, n_tokens = 655, progress = 0.77, t = 28.77 s / 22.76 tokens per second 48.31.464.046 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 774, progress = 0.99, t = 28.77 s / 26.90 tokens per second 48.31.468.853 I slot print_timing: id 3 | task 9011 | prompt processing, n_tokens = 770, progress = 0.99, t = 28.77 s / 26.76 tokens per second 48.34.189.775 I slot print_timing: id 0 | task 9014 | prompt eval time = 19328.97 ms / 147 tokens ( 131.49 ms per token, 7.61 tokens per second) 48.34.189.777 I slot print_timing: id 0 | task 9014 | eval time = 2731.04 ms / 2 tokens ( 2731.04 ms per token, 0.37 tokens per second) 48.34.189.778 I slot print_timing: id 0 | task 9014 | total time = 22060.01 ms / 149 tokens 48.34.189.778 I slot print_timing: id 0 | task 9014 | graphs reused = 7886 48.34.189.779 I slot print_timing: id 0 | task 9014 | graph reallocs = 0 / 0 (same size) / (changed size) 48.34.189.815 I slot release: id 0 | task 9014 | stop processing: n_tokens = 803, truncated = 0 48.34.190.324 I slot print_timing: id 1 | task 9009 | prompt processing, n_tokens = 851, progress = 1.00, t = 31.50 s / 27.01 tokens per second 48.34.560.171 I slot print_timing: id 2 | task 9010 | prompt eval time = 31504.44 ms / 778 tokens ( 40.49 ms per token, 24.69 tokens per second) 48.34.560.174 I slot print_timing: id 2 | task 9010 | eval time = 370.10 ms / 2 tokens ( 370.10 ms per token, 2.70 tokens per second) 48.34.560.174 I slot print_timing: id 2 | task 9010 | total time = 31874.54 ms / 780 tokens 48.34.560.175 I slot print_timing: id 2 | task 9010 | graphs reused = 7886 48.34.560.175 I slot print_timing: id 2 | task 9010 | graph reallocs = 0 / 0 (same size) / (changed size) 48.34.560.209 I slot release: id 2 | task 9010 | stop processing: n_tokens = 779, truncated = 0 48.34.560.358 I slot print_timing: id 3 | task 9011 | prompt eval time = 31504.62 ms / 774 tokens ( 40.70 ms per token, 24.57 tokens per second) 48.34.560.360 I slot print_timing: id 3 | task 9011 | eval time = 370.04 ms / 2 tokens ( 370.04 ms per token, 2.70 tokens per second) 48.34.560.361 I slot print_timing: id 3 | task 9011 | total time = 31874.66 ms / 776 tokens 48.34.560.361 I slot print_timing: id 3 | task 9011 | graphs reused = 7886 48.34.560.361 I slot print_timing: id 3 | task 9011 | graph reallocs = 0 / 0 (same size) / (changed size) 48.34.560.386 I slot release: id 3 | task 9011 | stop processing: n_tokens = 775, truncated = 0 48.34.560.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 81709931620 48.34.560.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.839 MiB) 48.34.585.873 I slot launch_slot_: id 0 | task 9019 | processing task, is_child = 0 48.34.585.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 48.34.604.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.965 MiB) 48.34.622.358 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 81710302014 48.34.622.463 I slot launch_slot_: id 2 | task 9020 | processing task, is_child = 0 48.34.622.506 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 81710302191 48.34.622.568 I slot launch_slot_: id 3 | task 9021 | processing task, is_child = 0 48.41.273.794 I slot print_timing: id 1 | task 9009 | prompt eval time = 31874.47 ms / 855 tokens ( 37.28 ms per token, 26.82 tokens per second) 48.41.273.796 I slot print_timing: id 1 | task 9009 | eval time = 6713.76 ms / 2 tokens ( 6713.76 ms per token, 0.15 tokens per second) 48.41.273.796 I slot print_timing: id 1 | task 9009 | total time = 38588.22 ms / 857 tokens 48.41.273.797 I slot print_timing: id 1 | task 9009 | graphs reused = 7886 48.41.273.797 I slot print_timing: id 1 | task 9009 | graph reallocs = 0 / 0 (same size) / (changed size) 48.41.273.833 I slot release: id 1 | task 9009 | stop processing: n_tokens = 856, truncated = 0 48.41.273.845 I slot print_timing: id 0 | task 9019 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.65 s / 27.51 tokens per second 48.41.280.765 I slot print_timing: id 2 | task 9020 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.65 s / 27.51 tokens per second 48.41.285.237 I slot print_timing: id 3 | task 9021 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.65 s / 27.52 tokens per second 48.43.122.389 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 81717015638 48.43.122.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.473 MiB) 48.46.719.470 I slot launch_slot_: id 1 | task 9024 | processing task, is_child = 0 48.46.719.483 I slot print_timing: id 0 | task 9019 | prompt processing, n_tokens = 333, progress = 0.34, t = 8.50 s / 39.18 tokens per second 48.46.719.569 I slot print_timing: id 2 | task 9020 | prompt processing, n_tokens = 333, progress = 0.35, t = 8.50 s / 39.18 tokens per second 48.46.719.575 I slot print_timing: id 3 | task 9021 | prompt processing, n_tokens = 333, progress = 0.35, t = 8.50 s / 39.18 tokens per second 48.52.586.320 I slot print_timing: id 0 | task 9019 | prompt processing, n_tokens = 455, progress = 0.47, t = 17.96 s / 25.33 tokens per second 48.53.014.246 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 183, progress = 0.19, t = 5.87 s / 31.19 tokens per second 48.53.018.948 I slot print_timing: id 2 | task 9020 | prompt processing, n_tokens = 428, progress = 0.45, t = 17.96 s / 23.83 tokens per second 48.53.023.825 I slot print_timing: id 3 | task 9021 | prompt processing, n_tokens = 448, progress = 0.46, t = 17.96 s / 24.94 tokens per second 49.08.235.389 I slot print_timing: id 0 | task 9019 | prompt processing, n_tokens = 836, progress = 0.86, t = 33.61 s / 24.87 tokens per second 49.08.664.833 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 333, progress = 0.35, t = 21.52 s / 15.48 tokens per second 49.08.664.845 I slot print_timing: id 2 | task 9020 | prompt processing, n_tokens = 836, progress = 0.89, t = 33.61 s / 24.87 tokens per second 49.08.669.241 I slot print_timing: id 3 | task 9021 | prompt processing, n_tokens = 836, progress = 0.87, t = 33.61 s / 24.87 tokens per second 49.14.498.692 I slot print_timing: id 0 | task 9019 | prompt processing, n_tokens = 967, progress = 1.00, t = 39.88 s / 24.25 tokens per second 49.14.927.795 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 431, progress = 0.46, t = 27.78 s / 15.52 tokens per second 49.14.932.222 I slot print_timing: id 2 | task 9020 | prompt processing, n_tokens = 940, progress = 1.00, t = 39.88 s / 23.57 tokens per second 49.14.936.758 I slot print_timing: id 3 | task 9021 | prompt processing, n_tokens = 960, progress = 1.00, t = 39.88 s / 24.07 tokens per second 49.19.985.846 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 836, progress = 0.88, t = 33.27 s / 25.13 tokens per second 49.21.825.481 I slot print_timing: id 0 | task 9019 | prompt eval time = 45362.89 ms / 971 tokens ( 46.72 ms per token, 21.41 tokens per second) 49.21.825.484 I slot print_timing: id 0 | task 9019 | eval time = 1840.01 ms / 2 tokens ( 1840.01 ms per token, 0.54 tokens per second) 49.21.825.484 I slot print_timing: id 0 | task 9019 | total time = 47202.90 ms / 973 tokens 49.21.825.485 I slot print_timing: id 0 | task 9019 | graphs reused = 7886 49.21.825.485 I slot print_timing: id 0 | task 9019 | graph reallocs = 0 / 0 (same size) / (changed size) 49.21.825.533 I slot release: id 0 | task 9019 | stop processing: n_tokens = 972, truncated = 0 49.21.825.771 I slot print_timing: id 2 | task 9020 | prompt eval time = 45362.99 ms / 944 tokens ( 48.05 ms per token, 20.81 tokens per second) 49.21.825.774 I slot print_timing: id 2 | task 9020 | eval time = 1840.13 ms / 2 tokens ( 1840.13 ms per token, 0.54 tokens per second) 49.21.825.774 I slot print_timing: id 2 | task 9020 | total time = 47203.12 ms / 946 tokens 49.21.825.774 I slot print_timing: id 2 | task 9020 | graphs reused = 7886 49.21.825.775 I slot print_timing: id 2 | task 9020 | graph reallocs = 0 / 0 (same size) / (changed size) 49.21.825.799 I slot release: id 2 | task 9020 | stop processing: n_tokens = 945, truncated = 0 49.21.826.019 I slot print_timing: id 3 | task 9021 | prompt eval time = 45363.13 ms / 964 tokens ( 47.06 ms per token, 21.25 tokens per second) 49.21.826.027 I slot print_timing: id 3 | task 9021 | eval time = 1840.19 ms / 2 tokens ( 1840.19 ms per token, 0.54 tokens per second) 49.21.826.028 I slot print_timing: id 3 | task 9021 | total time = 47203.32 ms / 966 tokens 49.21.826.028 I slot print_timing: id 3 | task 9021 | graphs reused = 7886 49.21.826.028 I slot print_timing: id 3 | task 9021 | graph reallocs = 0 / 0 (same size) / (changed size) 49.21.826.054 I slot release: id 3 | task 9021 | stop processing: n_tokens = 965, truncated = 0 49.21.826.061 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 943, progress = 1.00, t = 35.11 s / 26.86 tokens per second 49.22.014.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 972, t_last = 81757567338 49.22.014.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.099 MiB) 49.22.036.763 I slot launch_slot_: id 0 | task 9031 | processing task, is_child = 0 49.22.036.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 826.910 MiB) 49.22.059.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 797.712 MiB) 49.22.078.144 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 81757567604 49.22.078.252 I slot launch_slot_: id 2 | task 9032 | processing task, is_child = 0 49.22.078.303 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.895 49.22.078.323 I slot launch_slot_: id 3 | task 9033 | processing task, is_child = 0 49.28.071.320 I slot print_timing: id 1 | task 9024 | prompt eval time = 35295.16 ms / 947 tokens ( 37.27 ms per token, 26.83 tokens per second) 49.28.071.322 I slot print_timing: id 1 | task 9024 | eval time = 6056.66 ms / 2 tokens ( 6056.66 ms per token, 0.17 tokens per second) 49.28.071.323 I slot print_timing: id 1 | task 9024 | total time = 41351.82 ms / 949 tokens 49.28.071.323 I slot print_timing: id 1 | task 9024 | graphs reused = 7886 49.28.071.324 I slot print_timing: id 1 | task 9024 | graph reallocs = 0 / 0 (same size) / (changed size) 49.28.071.360 I slot release: id 1 | task 9024 | stop processing: n_tokens = 948, truncated = 0 49.28.071.372 I slot print_timing: id 0 | task 9031 | prompt processing, n_tokens = 162, progress = 0.20, t = 5.99 s / 27.03 tokens per second 49.28.077.307 I slot print_timing: id 2 | task 9032 | prompt processing, n_tokens = 162, progress = 0.20, t = 5.99 s / 27.03 tokens per second 49.28.082.098 I slot print_timing: id 3 | task 9033 | prompt processing, n_tokens = 129, progress = 1.00, t = 5.99 s / 21.53 tokens per second 49.31.235.175 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 81763813165 49.31.235.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.712 MiB) 49.31.256.236 I slot launch_slot_: id 1 | task 9036 | processing task, is_child = 0 49.31.256.247 I slot print_timing: id 0 | task 9031 | prompt processing, n_tokens = 282, progress = 0.35, t = 9.16 s / 30.80 tokens per second 49.31.260.719 I slot print_timing: id 2 | task 9032 | prompt processing, n_tokens = 283, progress = 0.35, t = 9.16 s / 30.91 tokens per second 49.42.589.191 I slot print_timing: id 3 | task 9033 | prompt eval time = 9156.69 ms / 133 tokens ( 68.85 ms per token, 14.52 tokens per second) 49.42.589.196 I slot print_timing: id 3 | task 9033 | eval time = 11354.02 ms / 2 tokens (11354.02 ms per token, 0.09 tokens per second) 49.42.589.197 I slot print_timing: id 3 | task 9033 | total time = 20510.71 ms / 135 tokens 49.42.589.197 I slot print_timing: id 3 | task 9033 | graphs reused = 7886 49.42.589.198 I slot print_timing: id 3 | task 9033 | graph reallocs = 0 / 0 (same size) / (changed size) 49.42.589.234 I slot release: id 3 | task 9033 | stop processing: n_tokens = 970, truncated = 0 49.42.589.246 I slot print_timing: id 0 | task 9031 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.51 s / 33.10 tokens per second 49.42.595.356 I slot print_timing: id 1 | task 9036 | prompt processing, n_tokens = 137, progress = 0.14, t = 11.33 s / 12.09 tokens per second 49.42.600.151 I slot print_timing: id 2 | task 9032 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.51 s / 33.10 tokens per second 49.46.791.214 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 81778331039 49.46.791.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.901 MiB) 49.47.927.155 I slot launch_slot_: id 3 | task 9039 | processing task, is_child = 0 49.47.927.168 I slot print_timing: id 0 | task 9031 | prompt processing, n_tokens = 794, progress = 0.99, t = 24.71 s / 32.13 tokens per second 49.47.931.660 I slot print_timing: id 1 | task 9036 | prompt processing, n_tokens = 335, progress = 0.34, t = 15.53 s / 21.57 tokens per second 49.47.931.670 I slot print_timing: id 2 | task 9032 | prompt processing, n_tokens = 795, progress = 0.99, t = 24.71 s / 32.17 tokens per second 49.51.589.973 I slot print_timing: id 1 | task 9036 | prompt processing, n_tokens = 459, progress = 0.47, t = 20.33 s / 22.58 tokens per second 49.51.597.325 I slot print_timing: id 3 | task 9039 | prompt processing, n_tokens = 137, progress = 0.14, t = 3.65 s / 37.50 tokens per second 49.58.793.297 I slot print_timing: id 0 | task 9031 | prompt eval time = 29511.45 ms / 798 tokens ( 36.98 ms per token, 27.04 tokens per second) 49.58.793.308 I slot print_timing: id 0 | task 9031 | eval time = 7203.52 ms / 2 tokens ( 7203.52 ms per token, 0.14 tokens per second) 49.58.793.308 I slot print_timing: id 0 | task 9031 | total time = 36714.96 ms / 800 tokens 49.58.793.308 I slot print_timing: id 0 | task 9031 | graphs reused = 7886 49.58.793.309 I slot print_timing: id 0 | task 9031 | graph reallocs = 0 / 0 (same size) / (changed size) 49.58.793.350 I slot release: id 0 | task 9031 | stop processing: n_tokens = 799, truncated = 0 49.58.793.511 I slot print_timing: id 2 | task 9032 | prompt eval time = 29511.55 ms / 799 tokens ( 36.94 ms per token, 27.07 tokens per second) 49.58.793.514 I slot print_timing: id 2 | task 9032 | eval time = 7203.55 ms / 2 tokens ( 7203.55 ms per token, 0.14 tokens per second) 49.58.793.514 I slot print_timing: id 2 | task 9032 | total time = 36715.10 ms / 801 tokens 49.58.793.514 I slot print_timing: id 2 | task 9032 | graphs reused = 7886 49.58.793.515 I slot print_timing: id 2 | task 9032 | graph reallocs = 0 / 0 (same size) / (changed size) 49.58.793.537 I slot release: id 2 | task 9032 | stop processing: n_tokens = 800, truncated = 0 49.58.793.546 I slot print_timing: id 1 | task 9036 | prompt processing, n_tokens = 826, progress = 0.85, t = 27.53 s / 30.00 tokens per second 49.58.801.168 I slot print_timing: id 3 | task 9039 | prompt processing, n_tokens = 335, progress = 0.35, t = 10.86 s / 30.86 tokens per second 50.00.646.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 81794535155 50.00.646.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.901 MiB) 50.02.109.997 I slot launch_slot_: id 0 | task 9043 | processing task, is_child = 0 50.02.110.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.337 MiB) 50.02.129.303 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 81794535342 50.02.129.393 I slot launch_slot_: id 2 | task 9044 | processing task, is_child = 0 50.02.129.477 I slot print_timing: id 1 | task 9036 | prompt processing, n_tokens = 971, progress = 1.00, t = 29.39 s / 33.04 tokens per second 50.02.134.218 I slot print_timing: id 3 | task 9039 | prompt processing, n_tokens = 437, progress = 0.46, t = 12.71 s / 34.38 tokens per second 50.10.484.759 I slot print_timing: id 0 | task 9043 | prompt processing, n_tokens = 137, progress = 0.14, t = 8.36 s / 16.40 tokens per second 50.10.490.472 I slot print_timing: id 2 | task 9044 | prompt processing, n_tokens = 139, progress = 0.15, t = 8.35 s / 16.65 tokens per second 50.10.494.894 I slot print_timing: id 3 | task 9039 | prompt processing, n_tokens = 826, progress = 0.87, t = 22.55 s / 36.63 tokens per second 50.16.881.288 I slot print_timing: id 1 | task 9036 | prompt eval time = 39224.09 ms / 975 tokens ( 40.23 ms per token, 24.86 tokens per second) 50.16.881.293 I slot print_timing: id 1 | task 9036 | eval time = 6396.53 ms / 2 tokens ( 6396.53 ms per token, 0.16 tokens per second) 50.16.881.294 I slot print_timing: id 1 | task 9036 | total time = 45620.63 ms / 977 tokens 50.16.881.294 I slot print_timing: id 1 | task 9036 | graphs reused = 7886 50.16.881.295 I slot print_timing: id 1 | task 9036 | graph reallocs = 0 / 0 (same size) / (changed size) 50.16.881.339 I slot release: id 1 | task 9036 | stop processing: n_tokens = 976, truncated = 0 50.16.881.351 I slot print_timing: id 0 | task 9043 | prompt processing, n_tokens = 335, progress = 0.35, t = 14.75 s / 22.71 tokens per second 50.16.881.360 I slot print_timing: id 2 | task 9044 | prompt processing, n_tokens = 304, progress = 0.33, t = 14.75 s / 20.61 tokens per second 50.16.881.366 I slot print_timing: id 3 | task 9039 | prompt processing, n_tokens = 949, progress = 1.00, t = 28.94 s / 32.79 tokens per second 50.20.023.537 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 81812623144 50.20.023.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.836 MiB) 50.20.044.063 I slot launch_slot_: id 1 | task 9048 | processing task, is_child = 0 50.20.044.075 I slot print_timing: id 0 | task 9043 | prompt processing, n_tokens = 445, progress = 0.46, t = 17.89 s / 24.87 tokens per second 50.20.048.622 I slot print_timing: id 2 | task 9044 | prompt processing, n_tokens = 414, progress = 0.45, t = 17.89 s / 23.14 tokens per second 50.30.968.541 I slot print_timing: id 3 | task 9039 | prompt eval time = 32087.38 ms / 953 tokens ( 33.67 ms per token, 29.70 tokens per second) 50.30.968.544 I slot print_timing: id 3 | task 9039 | eval time = 10945.01 ms / 2 tokens (10945.01 ms per token, 0.09 tokens per second) 50.30.968.545 I slot print_timing: id 3 | task 9039 | total time = 43032.39 ms / 955 tokens 50.30.968.545 I slot print_timing: id 3 | task 9039 | graphs reused = 7886 50.30.968.545 I slot print_timing: id 3 | task 9039 | graph reallocs = 0 / 0 (same size) / (changed size) 50.30.968.588 I slot release: id 3 | task 9039 | stop processing: n_tokens = 954, truncated = 0 50.30.968.599 I slot print_timing: id 0 | task 9043 | prompt processing, n_tokens = 826, progress = 0.86, t = 28.84 s / 28.64 tokens per second 50.30.974.467 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 139, progress = 0.15, t = 10.92 s / 12.73 tokens per second 50.30.979.329 I slot print_timing: id 2 | task 9044 | prompt processing, n_tokens = 779, progress = 0.84, t = 28.83 s / 27.02 tokens per second 50.36.161.946 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 81826710393 50.36.162.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.586 MiB) 50.36.591.535 I slot launch_slot_: id 3 | task 9051 | processing task, is_child = 0 50.36.591.548 I slot print_timing: id 0 | task 9043 | prompt processing, n_tokens = 957, progress = 1.00, t = 34.03 s / 28.12 tokens per second 50.36.596.089 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 304, progress = 0.34, t = 16.11 s / 18.87 tokens per second 50.36.596.097 I slot print_timing: id 2 | task 9044 | prompt processing, n_tokens = 926, progress = 1.00, t = 34.03 s / 27.21 tokens per second 50.39.907.208 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 382, progress = 0.43, t = 19.86 s / 19.24 tokens per second 50.39.914.381 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 139, progress = 0.15, t = 3.31 s / 42.04 tokens per second 50.47.110.135 I slot print_timing: id 0 | task 9043 | prompt eval time = 37777.63 ms / 961 tokens ( 39.31 ms per token, 25.44 tokens per second) 50.47.110.140 I slot print_timing: id 0 | task 9043 | eval time = 7203.10 ms / 2 tokens ( 7203.10 ms per token, 0.14 tokens per second) 50.47.110.141 I slot print_timing: id 0 | task 9043 | total time = 44980.73 ms / 963 tokens 50.47.110.141 I slot print_timing: id 0 | task 9043 | graphs reused = 7886 50.47.110.141 I slot print_timing: id 0 | task 9043 | graph reallocs = 0 / 0 (same size) / (changed size) 50.47.110.180 I slot release: id 0 | task 9043 | stop processing: n_tokens = 962, truncated = 0 50.47.110.400 I slot print_timing: id 2 | task 9044 | prompt eval time = 37773.03 ms / 930 tokens ( 40.62 ms per token, 24.62 tokens per second) 50.47.110.406 I slot print_timing: id 2 | task 9044 | eval time = 7203.20 ms / 2 tokens ( 7203.20 ms per token, 0.14 tokens per second) 50.47.110.407 I slot print_timing: id 2 | task 9044 | total time = 44976.23 ms / 932 tokens 50.47.110.407 I slot print_timing: id 2 | task 9044 | graphs reused = 7886 50.47.110.407 I slot print_timing: id 2 | task 9044 | graph reallocs = 0 / 0 (same size) / (changed size) 50.47.110.438 I slot release: id 2 | task 9044 | stop processing: n_tokens = 931, truncated = 0 50.47.110.445 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 779, progress = 0.87, t = 27.06 s / 28.79 tokens per second 50.47.117.533 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 304, progress = 0.34, t = 10.51 s / 28.93 tokens per second 50.48.603.033 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 50.48.603.096 I slot launch_slot_: id 2 | task 9055 | processing task, is_child = 0 50.48.603.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 50.49.740.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 81842851985 50.49.740.904 I slot launch_slot_: id 0 | task 9056 | processing task, is_child = 0 50.49.740.991 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 894, progress = 1.00, t = 28.55 s / 31.31 tokens per second 50.49.753.035 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 386, progress = 0.43, t = 12.00 s / 32.16 tokens per second 50.57.776.906 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 139, progress = 0.15, t = 8.04 s / 17.30 tokens per second 50.57.783.236 I slot print_timing: id 2 | task 9055 | prompt processing, n_tokens = 107, progress = 1.00, t = 8.03 s / 13.32 tokens per second 50.57.787.750 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 779, progress = 0.86, t = 21.18 s / 36.79 tokens per second 51.01.828.180 I slot print_timing: id 1 | task 9048 | prompt eval time = 37728.36 ms / 898 tokens ( 42.01 ms per token, 23.80 tokens per second) 51.01.828.182 I slot print_timing: id 1 | task 9048 | eval time = 4051.28 ms / 2 tokens ( 4051.28 ms per token, 0.25 tokens per second) 51.01.828.183 I slot print_timing: id 1 | task 9048 | total time = 41779.63 ms / 900 tokens 51.01.828.183 I slot print_timing: id 1 | task 9048 | graphs reused = 7886 51.01.828.184 I slot print_timing: id 1 | task 9048 | graph reallocs = 0 / 0 (same size) / (changed size) 51.01.828.226 I slot release: id 1 | task 9048 | stop processing: n_tokens = 899, truncated = 0 51.01.828.445 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 304, progress = 0.34, t = 12.09 s / 25.15 tokens per second 51.01.828.457 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 898, progress = 1.00, t = 25.23 s / 35.60 tokens per second 51.03.323.167 I slot print_timing: id 2 | task 9055 | prompt eval time = 12082.93 ms / 111 tokens ( 108.86 ms per token, 9.19 tokens per second) 51.03.323.170 I slot print_timing: id 2 | task 9055 | eval time = 1494.72 ms / 2 tokens ( 1494.72 ms per token, 0.67 tokens per second) 51.03.323.170 I slot print_timing: id 2 | task 9055 | total time = 13577.65 ms / 113 tokens 51.03.323.171 I slot print_timing: id 2 | task 9055 | graphs reused = 7886 51.03.323.171 I slot print_timing: id 2 | task 9055 | graph reallocs = 0 / 0 (same size) / (changed size) 51.03.323.219 I slot release: id 2 | task 9055 | stop processing: n_tokens = 891, truncated = 0 51.03.323.398 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 81857570031 51.03.323.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.903 MiB) 51.03.344.481 I slot launch_slot_: id 1 | task 9060 | processing task, is_child = 0 51.03.344.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.215 MiB) 51.03.363.161 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 81859065024 51.03.363.257 I slot launch_slot_: id 2 | task 9061 | processing task, is_child = 0 51.03.363.265 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 383, progress = 0.43, t = 13.58 s / 28.20 tokens per second 51.12.633.613 I slot print_timing: id 3 | task 9051 | prompt eval time = 26722.81 ms / 902 tokens ( 29.63 ms per token, 33.75 tokens per second) 51.12.633.615 I slot print_timing: id 3 | task 9051 | eval time = 9310.21 ms / 2 tokens ( 9310.21 ms per token, 0.11 tokens per second) 51.12.633.616 I slot print_timing: id 3 | task 9051 | total time = 36033.02 ms / 904 tokens 51.12.633.616 I slot print_timing: id 3 | task 9051 | graphs reused = 7886 51.12.633.617 I slot print_timing: id 3 | task 9051 | graph reallocs = 0 / 0 (same size) / (changed size) 51.12.633.657 I slot release: id 3 | task 9051 | stop processing: n_tokens = 903, truncated = 0 51.12.633.667 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 779, progress = 0.87, t = 22.89 s / 34.03 tokens per second 51.12.639.552 I slot print_timing: id 1 | task 9060 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.27 s / 20.40 tokens per second 51.12.644.335 I slot print_timing: id 2 | task 9061 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.27 s / 20.40 tokens per second 51.16.660.560 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 81868375462 51.16.660.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.466 MiB) 51.19.217.959 I slot launch_slot_: id 3 | task 9064 | processing task, is_child = 0 51.19.217.981 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 895, progress = 1.00, t = 26.92 s / 33.25 tokens per second 51.19.222.535 I slot print_timing: id 1 | task 9060 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.29 s / 30.24 tokens per second 51.19.222.548 I slot print_timing: id 2 | task 9061 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.29 s / 30.24 tokens per second 51.29.353.338 I slot print_timing: id 1 | task 9060 | prompt processing, n_tokens = 709, progress = 0.58, t = 25.99 s / 27.28 tokens per second 51.29.359.532 I slot print_timing: id 2 | task 9061 | prompt processing, n_tokens = 720, progress = 0.58, t = 25.99 s / 27.71 tokens per second 51.29.363.968 I slot print_timing: id 3 | task 9064 | prompt processing, n_tokens = 189, progress = 0.15, t = 10.13 s / 18.66 tokens per second 51.40.129.798 I slot print_timing: id 0 | task 9056 | prompt eval time = 39612.41 ms / 899 tokens ( 44.06 ms per token, 22.69 tokens per second) 51.40.129.803 I slot print_timing: id 0 | task 9056 | eval time = 10776.47 ms / 2 tokens (10776.47 ms per token, 0.09 tokens per second) 51.40.129.803 I slot print_timing: id 0 | task 9056 | total time = 50388.88 ms / 901 tokens 51.40.129.804 I slot print_timing: id 0 | task 9056 | graphs reused = 7886 51.40.129.804 I slot print_timing: id 0 | task 9056 | graph reallocs = 0 / 0 (same size) / (changed size) 51.40.129.844 I slot release: id 0 | task 9056 | stop processing: n_tokens = 900, truncated = 0 51.40.129.858 I slot print_timing: id 1 | task 9060 | prompt processing, n_tokens = 1061, progress = 0.87, t = 36.76 s / 28.86 tokens per second 51.40.136.322 I slot print_timing: id 2 | task 9061 | prompt processing, n_tokens = 1061, progress = 0.86, t = 36.76 s / 28.86 tokens per second 51.40.149.101 I slot print_timing: id 3 | task 9064 | prompt processing, n_tokens = 402, progress = 0.31, t = 20.91 s / 19.23 tokens per second 51.46.000.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 81895871649 51.46.000.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.403 MiB) 51.48.553.061 I slot launch_slot_: id 0 | task 9068 | processing task, is_child = 0 51.48.553.147 I slot print_timing: id 1 | task 9060 | prompt processing, n_tokens = 1221, progress = 1.00, t = 42.63 s / 28.64 tokens per second 51.48.557.707 I slot print_timing: id 2 | task 9061 | prompt processing, n_tokens = 1232, progress = 1.00, t = 42.63 s / 28.90 tokens per second 51.48.562.224 I slot print_timing: id 3 | task 9064 | prompt processing, n_tokens = 774, progress = 0.60, t = 26.78 s / 28.90 tokens per second 51.56.865.934 I slot print_timing: id 0 | task 9068 | prompt processing, n_tokens = 402, progress = 0.16, t = 8.31 s / 48.36 tokens per second 51.56.872.347 I slot print_timing: id 3 | task 9064 | prompt processing, n_tokens = 1061, progress = 0.82, t = 37.64 s / 28.19 tokens per second 52.06.098.748 I slot print_timing: id 1 | task 9060 | prompt eval time = 53497.90 ms / 1225 tokens ( 43.67 ms per token, 22.90 tokens per second) 52.06.098.753 I slot print_timing: id 1 | task 9060 | eval time = 9233.15 ms / 2 tokens ( 9233.15 ms per token, 0.11 tokens per second) 52.06.098.753 I slot print_timing: id 1 | task 9060 | total time = 62731.05 ms / 1227 tokens 52.06.098.754 I slot print_timing: id 1 | task 9060 | graphs reused = 7886 52.06.098.754 I slot print_timing: id 1 | task 9060 | graph reallocs = 0 / 0 (same size) / (changed size) 52.06.098.806 I slot release: id 1 | task 9060 | stop processing: n_tokens = 1226, truncated = 0 52.06.099.046 I slot print_timing: id 2 | task 9061 | prompt eval time = 53498.16 ms / 1236 tokens ( 43.28 ms per token, 23.10 tokens per second) 52.06.099.051 I slot print_timing: id 2 | task 9061 | eval time = 9233.12 ms / 2 tokens ( 9233.12 ms per token, 0.11 tokens per second) 52.06.099.051 I slot print_timing: id 2 | task 9061 | total time = 62731.28 ms / 1238 tokens 52.06.099.052 I slot print_timing: id 2 | task 9061 | graphs reused = 7886 52.06.099.052 I slot print_timing: id 2 | task 9061 | graph reallocs = 0 / 0 (same size) / (changed size) 52.06.099.089 I slot release: id 2 | task 9061 | stop processing: n_tokens = 1237, truncated = 0 52.06.099.098 I slot print_timing: id 0 | task 9068 | prompt processing, n_tokens = 961, progress = 0.37, t = 17.55 s / 54.77 tokens per second 52.06.099.122 I slot print_timing: id 3 | task 9064 | prompt processing, n_tokens = 1286, progress = 1.00, t = 46.88 s / 27.43 tokens per second 52.18.954.115 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 81921840611 52.18.954.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.778 MiB) 52.18.990.190 I slot launch_slot_: id 1 | task 9072 | processing task, is_child = 0 52.18.990.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 52.19.024.281 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 81921840894 52.19.024.397 I slot launch_slot_: id 2 | task 9073 | processing task, is_child = 0 52.19.024.408 I slot print_timing: id 0 | task 9068 | prompt processing, n_tokens = 2071, progress = 0.80, t = 30.40 s / 68.12 tokens per second 52.31.135.250 I slot print_timing: id 3 | task 9064 | prompt eval time = 59731.55 ms / 1290 tokens ( 46.30 ms per token, 21.60 tokens per second) 52.31.135.255 I slot print_timing: id 3 | task 9064 | eval time = 12181.14 ms / 2 tokens (12181.14 ms per token, 0.08 tokens per second) 52.31.135.256 I slot print_timing: id 3 | task 9064 | total time = 71912.68 ms / 1292 tokens 52.31.135.257 I slot print_timing: id 3 | task 9064 | graphs reused = 7886 52.31.135.257 I slot print_timing: id 3 | task 9064 | graph reallocs = 0 / 0 (same size) / (changed size) 52.31.135.309 I slot release: id 3 | task 9064 | stop processing: n_tokens = 1291, truncated = 0 52.31.135.321 I slot print_timing: id 0 | task 9068 | prompt processing, n_tokens = 2288, progress = 0.88, t = 42.58 s / 53.73 tokens per second 52.31.141.772 I slot print_timing: id 1 | task 9072 | prompt processing, n_tokens = 402, progress = 0.16, t = 12.11 s / 33.21 tokens per second 52.31.146.638 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 402, progress = 0.15, t = 12.11 s / 33.21 tokens per second 52.47.095.964 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 81946877114 52.47.096.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 52.47.421.395 I slot launch_slot_: id 3 | task 9076 | processing task, is_child = 0 52.47.421.411 I slot print_timing: id 0 | task 9068 | prompt processing, n_tokens = 2583, progress = 1.00, t = 58.54 s / 44.12 tokens per second 52.47.426.275 I slot print_timing: id 1 | task 9072 | prompt processing, n_tokens = 961, progress = 0.38, t = 28.07 s / 34.24 tokens per second 52.47.426.300 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 961, progress = 0.35, t = 28.07 s / 34.24 tokens per second 53.11.028.675 I slot print_timing: id 1 | task 9072 | prompt processing, n_tokens = 1984, progress = 0.79, t = 52.00 s / 38.15 tokens per second 53.11.033.908 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 1982, progress = 0.72, t = 52.00 s / 38.12 tokens per second 53.22.398.560 I slot print_timing: id 0 | task 9068 | prompt eval time = 82475.59 ms / 2587 tokens ( 31.88 ms per token, 31.37 tokens per second) 53.22.398.564 I slot print_timing: id 0 | task 9068 | eval time = 11369.90 ms / 2 tokens (11369.90 ms per token, 0.09 tokens per second) 53.22.398.564 I slot print_timing: id 0 | task 9068 | total time = 93845.48 ms / 2589 tokens 53.22.398.565 I slot print_timing: id 0 | task 9068 | graphs reused = 7886 53.22.398.565 I slot print_timing: id 0 | task 9068 | graph reallocs = 0 / 0 (same size) / (changed size) 53.22.398.660 I slot release: id 0 | task 9068 | stop processing: n_tokens = 2588, truncated = 0 53.22.398.675 I slot print_timing: id 1 | task 9072 | prompt processing, n_tokens = 2288, progress = 0.92, t = 63.37 s / 36.11 tokens per second 53.22.405.133 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 2226, progress = 0.81, t = 63.37 s / 35.13 tokens per second 53.22.409.581 I slot print_timing: id 3 | task 9076 | prompt processing, n_tokens = 402, progress = 0.15, t = 11.36 s / 35.37 tokens per second 53.26.520.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 81998140467 53.26.520.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.153 MiB) 53.26.520.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.778 MiB) 53.32.278.916 I slot launch_slot_: id 0 | task 9080 | processing task, is_child = 0 53.32.279.105 I slot print_timing: id 1 | task 9072 | prompt processing, n_tokens = 2496, progress = 1.00, t = 67.49 s / 36.98 tokens per second 53.32.283.778 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 2288, progress = 0.83, t = 67.49 s / 33.90 tokens per second 53.32.288.438 I slot print_timing: id 3 | task 9076 | prompt processing, n_tokens = 961, progress = 0.36, t = 15.49 s / 62.05 tokens per second 53.53.766.462 I slot print_timing: id 0 | task 9080 | prompt processing, n_tokens = 208, progress = 0.12, t = 21.49 s / 9.68 tokens per second 53.53.773.421 I slot print_timing: id 2 | task 9073 | prompt processing, n_tokens = 2738, progress = 1.00, t = 94.74 s / 28.90 tokens per second 53.53.778.116 I slot print_timing: id 3 | task 9076 | prompt processing, n_tokens = 2139, progress = 0.81, t = 42.73 s / 50.06 tokens per second 53.59.645.764 I slot print_timing: id 1 | task 9072 | prompt eval time = 94737.63 ms / 2500 tokens ( 37.90 ms per token, 26.39 tokens per second) 53.59.645.767 I slot print_timing: id 1 | task 9072 | eval time = 5879.31 ms / 2 tokens ( 5879.31 ms per token, 0.17 tokens per second) 53.59.645.767 I slot print_timing: id 1 | task 9072 | total time = 100616.95 ms / 2502 tokens 53.59.645.768 I slot print_timing: id 1 | task 9072 | graphs reused = 7886 53.59.645.768 I slot print_timing: id 1 | task 9072 | graph reallocs = 0 / 0 (same size) / (changed size) 53.59.645.864 I slot release: id 1 | task 9072 | stop processing: n_tokens = 2501, truncated = 0 53.59.646.208 I slot print_timing: id 0 | task 9080 | prompt processing, n_tokens = 520, progress = 0.29, t = 27.37 s / 19.00 tokens per second 53.59.646.232 I slot print_timing: id 3 | task 9076 | prompt processing, n_tokens = 2288, progress = 0.86, t = 48.61 s / 47.07 tokens per second 54.12.820.193 I slot print_timing: id 2 | task 9073 | prompt eval time = 100617.30 ms / 2742 tokens ( 36.69 ms per token, 27.25 tokens per second) 54.12.820.198 I slot print_timing: id 2 | task 9073 | eval time = 13173.99 ms / 2 tokens (13173.99 ms per token, 0.08 tokens per second) 54.12.820.199 I slot print_timing: id 2 | task 9073 | total time = 113791.29 ms / 2744 tokens 54.12.820.199 I slot print_timing: id 2 | task 9073 | graphs reused = 7886 54.12.820.200 I slot print_timing: id 2 | task 9073 | graph reallocs = 0 / 0 (same size) / (changed size) 54.12.820.306 I slot release: id 2 | task 9073 | stop processing: n_tokens = 2743, truncated = 0 54.12.820.315 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 82035387671 54.12.820.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.278 MiB) 54.12.862.652 I slot launch_slot_: id 1 | task 9084 | processing task, is_child = 0 54.12.862.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.339 MiB) 54.12.906.078 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 82048562112 54.12.906.237 I slot launch_slot_: id 2 | task 9085 | processing task, is_child = 0 54.12.906.248 I slot print_timing: id 0 | task 9080 | prompt processing, n_tokens = 1263, progress = 0.71, t = 40.54 s / 31.15 tokens per second 54.12.911.080 I slot print_timing: id 3 | task 9076 | prompt processing, n_tokens = 2651, progress = 1.00, t = 61.79 s / 42.91 tokens per second 54.20.345.819 I slot print_timing: id 0 | task 9080 | prompt processing, n_tokens = 1447, progress = 0.81, t = 48.07 s / 30.10 tokens per second 54.20.353.157 I slot print_timing: id 1 | task 9084 | prompt processing, n_tokens = 208, progress = 0.11, t = 7.43 s / 27.98 tokens per second 54.20.357.705 I slot print_timing: id 2 | task 9085 | prompt processing, n_tokens = 208, progress = 0.10, t = 7.43 s / 27.98 tokens per second 54.31.689.613 I slot print_timing: id 3 | task 9076 | prompt eval time = 69311.88 ms / 2655 tokens ( 26.11 ms per token, 38.31 tokens per second) 54.31.689.617 I slot print_timing: id 3 | task 9076 | eval time = 11343.80 ms / 2 tokens (11343.80 ms per token, 0.09 tokens per second) 54.31.689.618 I slot print_timing: id 3 | task 9076 | total time = 80655.69 ms / 2657 tokens 54.31.689.618 I slot print_timing: id 3 | task 9076 | graphs reused = 7886 54.31.689.619 I slot print_timing: id 3 | task 9076 | graph reallocs = 0 / 0 (same size) / (changed size) 54.31.689.714 I slot release: id 3 | task 9076 | stop processing: n_tokens = 2656, truncated = 0 54.31.689.728 I slot print_timing: id 0 | task 9080 | prompt processing, n_tokens = 1775, progress = 1.00, t = 59.41 s / 29.88 tokens per second 54.31.696.539 I slot print_timing: id 1 | task 9084 | prompt processing, n_tokens = 520, progress = 0.28, t = 18.78 s / 27.69 tokens per second 54.31.696.564 I slot print_timing: id 2 | task 9085 | prompt processing, n_tokens = 520, progress = 0.25, t = 18.78 s / 27.69 tokens per second 54.51.850.378 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 82067431520 54.51.850.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.839 MiB) 54.51.895.846 I slot launch_slot_: id 3 | task 9089 | processing task, is_child = 0 54.51.895.863 I slot print_timing: id 1 | task 9084 | prompt processing, n_tokens = 1325, progress = 0.72, t = 38.94 s / 34.03 tokens per second 54.51.900.270 I slot print_timing: id 2 | task 9085 | prompt processing, n_tokens = 1447, progress = 0.71, t = 38.94 s / 37.16 tokens per second 54.57.291.726 I slot print_timing: id 0 | task 9080 | prompt eval time = 79571.44 ms / 1779 tokens ( 44.73 ms per token, 22.36 tokens per second) 54.57.291.731 I slot print_timing: id 0 | task 9080 | eval time = 5441.35 ms / 2 tokens ( 5441.35 ms per token, 0.18 tokens per second) 54.57.291.732 I slot print_timing: id 0 | task 9080 | total time = 85012.79 ms / 1781 tokens 54.57.291.732 I slot print_timing: id 0 | task 9080 | graphs reused = 7886 54.57.291.733 I slot print_timing: id 0 | task 9080 | graph reallocs = 0 / 0 (same size) / (changed size) 54.57.291.808 I slot release: id 0 | task 9080 | stop processing: n_tokens = 1780, truncated = 0 54.57.291.818 I slot print_timing: id 1 | task 9084 | prompt processing, n_tokens = 1447, progress = 0.79, t = 44.38 s / 32.60 tokens per second 54.57.298.151 I slot print_timing: id 2 | task 9085 | prompt processing, n_tokens = 1532, progress = 0.75, t = 44.38 s / 34.52 tokens per second 54.57.303.005 I slot print_timing: id 3 | task 9089 | prompt processing, n_tokens = 208, progress = 0.11, t = 5.39 s / 38.61 tokens per second 55.10.166.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 55.10.166.199 I slot launch_slot_: id 0 | task 9092 | processing task, is_child = 0 55.11.681.657 I slot print_timing: id 1 | task 9084 | prompt processing, n_tokens = 1837, progress = 1.00, t = 57.26 s / 32.08 tokens per second 55.11.686.351 I slot print_timing: id 2 | task 9085 | prompt processing, n_tokens = 2044, progress = 1.00, t = 57.26 s / 35.70 tokens per second 55.11.690.944 I slot print_timing: id 3 | task 9089 | prompt processing, n_tokens = 520, progress = 0.28, t = 18.26 s / 28.48 tokens per second 55.27.214.166 I slot print_timing: id 0 | task 9092 | prompt processing, n_tokens = 511, progress = 1.00, t = 17.05 s / 29.98 tokens per second 55.27.221.199 I slot print_timing: id 3 | task 9089 | prompt processing, n_tokens = 1336, progress = 0.72, t = 35.31 s / 37.84 tokens per second 55.29.085.562 I slot print_timing: id 1 | task 9084 | prompt eval time = 74303.21 ms / 1841 tokens ( 40.36 ms per token, 24.78 tokens per second) 55.29.085.568 I slot print_timing: id 1 | task 9084 | eval time = 1871.62 ms / 2 tokens ( 1871.62 ms per token, 0.53 tokens per second) 55.29.085.569 I slot print_timing: id 1 | task 9084 | total time = 76174.84 ms / 1843 tokens 55.29.085.569 I slot print_timing: id 1 | task 9084 | graphs reused = 7886 55.29.085.569 I slot print_timing: id 1 | task 9084 | graph reallocs = 0 / 0 (same size) / (changed size) 55.29.085.640 I slot release: id 1 | task 9084 | stop processing: n_tokens = 1842, truncated = 0 55.29.085.878 I slot print_timing: id 2 | task 9085 | prompt eval time = 74303.26 ms / 2048 tokens ( 36.28 ms per token, 27.56 tokens per second) 55.29.085.880 I slot print_timing: id 2 | task 9085 | eval time = 1871.72 ms / 2 tokens ( 1871.72 ms per token, 0.53 tokens per second) 55.29.085.881 I slot print_timing: id 2 | task 9085 | total time = 76174.98 ms / 2050 tokens 55.29.085.881 I slot print_timing: id 2 | task 9085 | graphs reused = 7886 55.29.085.881 I slot print_timing: id 2 | task 9085 | graph reallocs = 0 / 0 (same size) / (changed size) 55.29.085.935 I slot release: id 2 | task 9085 | stop processing: n_tokens = 2049, truncated = 0 55.29.085.944 I slot print_timing: id 3 | task 9089 | prompt processing, n_tokens = 1447, progress = 0.78, t = 37.18 s / 38.92 tokens per second 55.33.930.782 I slot print_timing: id 0 | task 9092 | prompt eval time = 18919.19 ms / 515 tokens ( 36.74 ms per token, 27.22 tokens per second) 55.33.930.784 I slot print_timing: id 0 | task 9092 | eval time = 4845.38 ms / 2 tokens ( 4845.38 ms per token, 0.21 tokens per second) 55.33.930.785 I slot print_timing: id 0 | task 9092 | total time = 23764.57 ms / 517 tokens 55.33.930.785 I slot print_timing: id 0 | task 9092 | graphs reused = 7886 55.33.930.786 I slot print_timing: id 0 | task 9092 | graph reallocs = 0 / 0 (same size) / (changed size) 55.33.930.863 I slot release: id 0 | task 9092 | stop processing: n_tokens = 1963, truncated = 0 55.33.930.874 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 82124827446 55.33.930.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 55.33.970.597 I slot launch_slot_: id 1 | task 9096 | processing task, is_child = 0 55.33.970.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.402 MiB) 55.34.007.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.784 MiB) 55.34.044.995 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 55.34.045.058 I slot launch_slot_: id 0 | task 9097 | processing task, is_child = 0 55.34.045.162 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 82124827740 55.34.045.278 I slot launch_slot_: id 2 | task 9098 | processing task, is_child = 0 55.34.053.099 I slot print_timing: id 3 | task 9089 | prompt processing, n_tokens = 1848, progress = 1.00, t = 42.03 s / 43.97 tokens per second 55.41.322.533 I slot print_timing: id 0 | task 9097 | prompt processing, n_tokens = 330, progress = 1.00, t = 7.28 s / 45.35 tokens per second 55.41.329.857 I slot print_timing: id 1 | task 9096 | prompt processing, n_tokens = 130, progress = 0.18, t = 7.27 s / 17.88 tokens per second 55.41.334.276 I slot print_timing: id 2 | task 9098 | prompt processing, n_tokens = 130, progress = 0.17, t = 7.27 s / 17.88 tokens per second 55.44.050.004 I slot print_timing: id 3 | task 9089 | prompt eval time = 49417.85 ms / 1852 tokens ( 26.68 ms per token, 37.48 tokens per second) 55.44.050.018 I slot print_timing: id 3 | task 9089 | eval time = 2727.48 ms / 2 tokens ( 2727.48 ms per token, 0.37 tokens per second) 55.44.050.019 I slot print_timing: id 3 | task 9089 | total time = 52145.33 ms / 1854 tokens 55.44.050.019 I slot print_timing: id 3 | task 9089 | graphs reused = 7886 55.44.050.020 I slot print_timing: id 3 | task 9089 | graph reallocs = 0 / 0 (same size) / (changed size) 55.44.050.094 I slot release: id 3 | task 9089 | stop processing: n_tokens = 1853, truncated = 0 55.44.050.107 I slot print_timing: id 1 | task 9096 | prompt processing, n_tokens = 210, progress = 0.29, t = 10.00 s / 21.01 tokens per second 55.44.056.753 I slot print_timing: id 2 | task 9098 | prompt processing, n_tokens = 232, progress = 0.31, t = 10.00 s / 23.21 tokens per second 55.53.264.827 I slot print_timing: id 0 | task 9097 | prompt eval time = 10004.52 ms / 334 tokens ( 29.95 ms per token, 33.38 tokens per second) 55.53.264.830 I slot print_timing: id 0 | task 9097 | eval time = 9215.01 ms / 2 tokens ( 9215.01 ms per token, 0.11 tokens per second) 55.53.264.831 I slot print_timing: id 0 | task 9097 | total time = 19219.54 ms / 336 tokens 55.53.264.832 I slot print_timing: id 0 | task 9097 | graphs reused = 7886 55.53.264.832 I slot print_timing: id 0 | task 9097 | graph reallocs = 0 / 0 (same size) / (changed size) 55.53.264.909 I slot release: id 0 | task 9097 | stop processing: n_tokens = 1782, truncated = 0 55.53.264.922 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 82139791899 55.53.265.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.472 MiB) 55.53.303.700 I slot launch_slot_: id 3 | task 9102 | processing task, is_child = 0 55.53.303.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 828.848 MiB) 55.53.348.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 82149006719 55.53.349.130 I slot launch_slot_: id 0 | task 9103 | processing task, is_child = 0 55.53.349.273 I slot print_timing: id 1 | task 9096 | prompt processing, n_tokens = 615, progress = 0.85, t = 19.21 s / 32.01 tokens per second 55.53.353.725 I slot print_timing: id 2 | task 9098 | prompt processing, n_tokens = 615, progress = 0.82, t = 19.21 s / 32.01 tokens per second 55.59.638.336 I slot print_timing: id 0 | task 9103 | prompt processing, n_tokens = 130, progress = 0.18, t = 6.29 s / 20.67 tokens per second 55.59.736.432 I slot print_timing: id 1 | task 9096 | prompt processing, n_tokens = 722, progress = 0.99, t = 25.59 s / 28.22 tokens per second 55.59.740.897 I slot print_timing: id 2 | task 9098 | prompt processing, n_tokens = 744, progress = 0.99, t = 25.59 s / 29.08 tokens per second 55.59.745.389 I slot print_timing: id 3 | task 9102 | prompt processing, n_tokens = 130, progress = 0.17, t = 6.28 s / 20.70 tokens per second 56.02.706.196 I slot print_timing: id 0 | task 9103 | prompt processing, n_tokens = 209, progress = 0.29, t = 9.36 s / 22.34 tokens per second 56.02.714.947 I slot print_timing: id 3 | task 9102 | prompt processing, n_tokens = 245, progress = 0.32, t = 9.35 s / 26.21 tokens per second 56.11.880.362 I slot print_timing: id 1 | task 9096 | prompt eval time = 28653.10 ms / 726 tokens ( 39.47 ms per token, 25.34 tokens per second) 56.11.880.364 I slot print_timing: id 1 | task 9096 | eval time = 9174.41 ms / 2 tokens ( 9174.41 ms per token, 0.11 tokens per second) 56.11.880.365 I slot print_timing: id 1 | task 9096 | total time = 37827.51 ms / 728 tokens 56.11.880.365 I slot print_timing: id 1 | task 9096 | graphs reused = 7886 56.11.880.365 I slot print_timing: id 1 | task 9096 | graph reallocs = 0 / 0 (same size) / (changed size) 56.11.880.398 I slot release: id 1 | task 9096 | stop processing: n_tokens = 727, truncated = 0 56.11.880.623 I slot print_timing: id 2 | task 9098 | prompt eval time = 28653.22 ms / 748 tokens ( 38.31 ms per token, 26.11 tokens per second) 56.11.880.629 I slot print_timing: id 2 | task 9098 | eval time = 9174.43 ms / 2 tokens ( 9174.43 ms per token, 0.11 tokens per second) 56.11.880.630 I slot print_timing: id 2 | task 9098 | total time = 37827.66 ms / 750 tokens 56.11.880.630 I slot print_timing: id 2 | task 9098 | graphs reused = 7886 56.11.880.630 I slot print_timing: id 2 | task 9098 | graph reallocs = 0 / 0 (same size) / (changed size) 56.11.880.655 I slot release: id 2 | task 9098 | stop processing: n_tokens = 749, truncated = 0 56.11.880.662 I slot print_timing: id 0 | task 9103 | prompt processing, n_tokens = 615, progress = 0.85, t = 18.53 s / 33.19 tokens per second 56.11.886.942 I slot print_timing: id 3 | task 9102 | prompt processing, n_tokens = 615, progress = 0.81, t = 18.52 s / 33.20 tokens per second 56.13.362.578 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 82167622203 56.13.362.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 909.940 MiB) 56.15.196.434 I slot launch_slot_: id 1 | task 9108 | processing task, is_child = 0 56.15.196.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 904.501 MiB) 56.15.214.612 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 56.15.214.660 I slot launch_slot_: id 2 | task 9109 | processing task, is_child = 0 56.15.214.668 I slot print_timing: id 0 | task 9103 | prompt processing, n_tokens = 721, progress = 0.99, t = 20.01 s / 36.03 tokens per second 56.15.226.738 I slot print_timing: id 3 | task 9102 | prompt processing, n_tokens = 757, progress = 0.99, t = 20.00 s / 37.84 tokens per second 56.18.643.349 I slot print_timing: id 1 | task 9108 | prompt processing, n_tokens = 117, progress = 0.15, t = 3.42 s / 34.17 tokens per second 56.18.649.831 I slot print_timing: id 2 | task 9109 | prompt processing, n_tokens = 120, progress = 0.99, t = 3.42 s / 35.05 tokens per second 56.20.962.261 I slot print_timing: id 0 | task 9103 | prompt eval time = 25293.98 ms / 725 tokens ( 34.89 ms per token, 28.66 tokens per second) 56.20.962.263 I slot print_timing: id 0 | task 9103 | eval time = 2319.14 ms / 2 tokens ( 2319.14 ms per token, 0.43 tokens per second) 56.20.962.264 I slot print_timing: id 0 | task 9103 | total time = 27613.12 ms / 727 tokens 56.20.962.264 I slot print_timing: id 0 | task 9103 | graphs reused = 7886 56.20.962.265 I slot print_timing: id 0 | task 9103 | graph reallocs = 0 / 0 (same size) / (changed size) 56.20.962.304 I slot release: id 0 | task 9103 | stop processing: n_tokens = 726, truncated = 0 56.20.962.709 I slot print_timing: id 3 | task 9102 | prompt eval time = 25285.17 ms / 761 tokens ( 33.23 ms per token, 30.10 tokens per second) 56.20.962.711 I slot print_timing: id 3 | task 9102 | eval time = 2319.37 ms / 2 tokens ( 2319.37 ms per token, 0.43 tokens per second) 56.20.962.711 I slot print_timing: id 3 | task 9102 | total time = 27604.54 ms / 763 tokens 56.20.962.711 I slot print_timing: id 3 | task 9102 | graphs reused = 7886 56.20.962.712 I slot print_timing: id 3 | task 9102 | graph reallocs = 0 / 0 (same size) / (changed size) 56.20.962.732 I slot release: id 3 | task 9102 | stop processing: n_tokens = 762, truncated = 0 56.20.962.741 I slot print_timing: id 1 | task 9108 | prompt processing, n_tokens = 257, progress = 0.32, t = 5.74 s / 44.75 tokens per second 56.21.493.069 I slot print_timing: id 2 | task 9109 | prompt eval time = 5743.32 ms / 124 tokens ( 46.32 ms per token, 21.59 tokens per second) 56.21.493.075 I slot print_timing: id 2 | task 9109 | eval time = 530.54 ms / 2 tokens ( 530.54 ms per token, 1.88 tokens per second) 56.21.493.076 I slot print_timing: id 2 | task 9109 | total time = 6273.86 ms / 126 tokens 56.21.493.076 I slot print_timing: id 2 | task 9109 | graphs reused = 7886 56.21.493.076 I slot print_timing: id 2 | task 9109 | graph reallocs = 0 / 0 (same size) / (changed size) 56.21.493.106 I slot release: id 2 | task 9109 | stop processing: n_tokens = 740, truncated = 0 56.21.493.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 82176704109 56.21.493.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.631 MiB) 56.21.512.963 I slot launch_slot_: id 0 | task 9113 | processing task, is_child = 0 56.21.513.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 914.192 MiB) 56.21.534.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.298 MiB) 56.21.556.851 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 82176704537 56.21.556.952 I slot launch_slot_: id 3 | task 9114 | processing task, is_child = 0 56.21.556.994 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 82177234911 56.21.557.059 I slot launch_slot_: id 2 | task 9115 | processing task, is_child = 0 56.21.557.131 I slot print_timing: id 1 | task 9108 | prompt processing, n_tokens = 282, progress = 0.35, t = 6.27 s / 44.95 tokens per second 56.31.264.724 I slot print_timing: id 0 | task 9113 | prompt processing, n_tokens = 155, progress = 0.19, t = 9.71 s / 15.97 tokens per second 56.31.448.253 I slot print_timing: id 1 | task 9108 | prompt processing, n_tokens = 631, progress = 0.79, t = 16.05 s / 39.33 tokens per second 56.31.452.658 I slot print_timing: id 2 | task 9115 | prompt processing, n_tokens = 155, progress = 0.19, t = 9.70 s / 15.97 tokens per second 56.31.457.094 I slot print_timing: id 3 | task 9114 | prompt processing, n_tokens = 163, progress = 0.16, t = 9.70 s / 16.80 tokens per second 56.37.965.198 I slot print_timing: id 0 | task 9113 | prompt processing, n_tokens = 277, progress = 0.34, t = 16.41 s / 16.88 tokens per second 56.37.965.209 I slot print_timing: id 1 | task 9108 | prompt processing, n_tokens = 794, progress = 0.99, t = 22.75 s / 34.91 tokens per second 56.39.090.507 I slot print_timing: id 2 | task 9115 | prompt processing, n_tokens = 277, progress = 0.35, t = 16.40 s / 16.89 tokens per second 56.39.090.518 I slot print_timing: id 3 | task 9114 | prompt processing, n_tokens = 352, progress = 0.34, t = 16.40 s / 21.46 tokens per second 56.42.106.285 I slot print_timing: id 0 | task 9113 | prompt processing, n_tokens = 293, progress = 0.36, t = 20.55 s / 14.26 tokens per second 56.42.113.423 I slot print_timing: id 2 | task 9115 | prompt processing, n_tokens = 283, progress = 0.35, t = 20.54 s / 13.77 tokens per second 56.42.117.862 I slot print_timing: id 3 | task 9114 | prompt processing, n_tokens = 526, progress = 0.50, t = 20.54 s / 25.60 tokens per second 56.55.687.602 I slot print_timing: id 1 | task 9108 | prompt eval time = 26887.11 ms / 798 tokens ( 33.69 ms per token, 29.68 tokens per second) 56.55.687.605 I slot print_timing: id 1 | task 9108 | eval time = 13581.33 ms / 2 tokens (13581.33 ms per token, 0.07 tokens per second) 56.55.687.605 I slot print_timing: id 1 | task 9108 | total time = 40468.44 ms / 800 tokens 56.55.687.606 I slot print_timing: id 1 | task 9108 | graphs reused = 7886 56.55.687.606 I slot print_timing: id 1 | task 9108 | graph reallocs = 0 / 0 (same size) / (changed size) 56.55.687.646 I slot release: id 1 | task 9108 | stop processing: n_tokens = 799, truncated = 0 56.55.687.660 I slot print_timing: id 0 | task 9113 | prompt processing, n_tokens = 679, progress = 0.84, t = 34.13 s / 19.89 tokens per second 56.55.693.696 I slot print_timing: id 2 | task 9115 | prompt processing, n_tokens = 679, progress = 0.85, t = 34.13 s / 19.90 tokens per second 56.55.698.524 I slot print_timing: id 3 | task 9114 | prompt processing, n_tokens = 893, progress = 0.86, t = 34.13 s / 26.17 tokens per second 57.00.089.248 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 82211429452 57.00.089.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.863 MiB) 57.00.526.728 I slot launch_slot_: id 1 | task 9121 | processing task, is_child = 0 57.00.526.740 I slot print_timing: id 0 | task 9113 | prompt processing, n_tokens = 805, progress = 1.00, t = 38.53 s / 20.89 tokens per second 57.00.538.817 I slot print_timing: id 2 | task 9115 | prompt processing, n_tokens = 795, progress = 0.99, t = 38.53 s / 20.63 tokens per second 57.00.543.354 I slot print_timing: id 3 | task 9114 | prompt processing, n_tokens = 1038, progress = 1.00, t = 38.53 s / 26.94 tokens per second 57.05.274.029 I slot print_timing: id 0 | task 9113 | prompt eval time = 41169.39 ms / 809 tokens ( 50.89 ms per token, 19.65 tokens per second) 57.05.274.032 I slot print_timing: id 0 | task 9113 | eval time = 2547.57 ms / 2 tokens ( 2547.57 ms per token, 0.39 tokens per second) 57.05.274.032 I slot print_timing: id 0 | task 9113 | total time = 43716.96 ms / 811 tokens 57.05.274.033 I slot print_timing: id 0 | task 9113 | graphs reused = 7886 57.05.274.033 I slot print_timing: id 0 | task 9113 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.274.077 I slot release: id 0 | task 9113 | stop processing: n_tokens = 810, truncated = 0 57.05.274.236 I slot print_timing: id 2 | task 9115 | prompt eval time = 41165.10 ms / 799 tokens ( 51.52 ms per token, 19.41 tokens per second) 57.05.274.237 I slot print_timing: id 2 | task 9115 | eval time = 2547.57 ms / 2 tokens ( 2547.57 ms per token, 0.39 tokens per second) 57.05.274.237 I slot print_timing: id 2 | task 9115 | total time = 43712.67 ms / 801 tokens 57.05.274.238 I slot print_timing: id 2 | task 9115 | graphs reused = 7886 57.05.274.238 I slot print_timing: id 2 | task 9115 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.274.263 I slot release: id 2 | task 9115 | stop processing: n_tokens = 800, truncated = 0 57.05.274.426 I slot print_timing: id 3 | task 9114 | prompt eval time = 41165.24 ms / 1042 tokens ( 39.51 ms per token, 25.31 tokens per second) 57.05.274.430 I slot print_timing: id 3 | task 9114 | eval time = 2547.57 ms / 2 tokens ( 2547.57 ms per token, 0.39 tokens per second) 57.05.274.431 I slot print_timing: id 3 | task 9114 | total time = 43712.81 ms / 1044 tokens 57.05.274.431 I slot print_timing: id 3 | task 9114 | graphs reused = 7886 57.05.274.431 I slot print_timing: id 3 | task 9114 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.274.466 I slot release: id 3 | task 9114 | stop processing: n_tokens = 1043, truncated = 0 57.05.274.472 I slot print_timing: id 1 | task 9121 | prompt processing, n_tokens = 319, progress = 0.38, t = 4.74 s / 67.37 tokens per second 57.05.278.684 I slot print_timing: id 1 | task 9121 | prompt processing, n_tokens = 329, progress = 0.39, t = 4.74 s / 69.41 tokens per second 57.05.580.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 82221015882 57.10.251.176 I slot launch_slot_: id 0 | task 9126 | processing task, is_child = 0 57.10.251.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.240 MiB) 57.10.272.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.986 MiB) 57.10.296.554 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 82221016068 57.10.296.659 I slot launch_slot_: id 2 | task 9127 | processing task, is_child = 0 57.10.296.709 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 82221016271 57.10.296.783 I slot launch_slot_: id 3 | task 9128 | processing task, is_child = 0 57.10.296.859 I slot print_timing: id 1 | task 9121 | prompt processing, n_tokens = 723, progress = 0.86, t = 5.04 s / 143.39 tokens per second 57.16.146.457 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 138, progress = 0.16, t = 5.85 s / 23.59 tokens per second 57.16.913.524 I slot print_timing: id 1 | task 9121 | prompt processing, n_tokens = 841, progress = 1.00, t = 15.61 s / 53.88 tokens per second 57.16.918.042 I slot print_timing: id 2 | task 9127 | prompt processing, n_tokens = 138, progress = 0.15, t = 5.85 s / 23.61 tokens per second 57.16.922.447 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 138, progress = 0.15, t = 5.85 s / 23.61 tokens per second 57.23.741.768 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 319, progress = 0.38, t = 13.44 s / 23.73 tokens per second 57.23.741.778 I slot print_timing: id 2 | task 9127 | prompt processing, n_tokens = 319, progress = 0.35, t = 13.44 s / 23.73 tokens per second 57.23.741.784 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 319, progress = 0.35, t = 13.44 s / 23.73 tokens per second 57.26.238.545 I slot print_timing: id 1 | task 9121 | prompt eval time = 23202.99 ms / 845 tokens ( 27.46 ms per token, 36.42 tokens per second) 57.26.238.548 I slot print_timing: id 1 | task 9121 | eval time = 2496.78 ms / 2 tokens ( 2496.78 ms per token, 0.40 tokens per second) 57.26.238.548 I slot print_timing: id 1 | task 9121 | total time = 25699.77 ms / 847 tokens 57.26.238.549 I slot print_timing: id 1 | task 9121 | graphs reused = 7886 57.26.238.549 I slot print_timing: id 1 | task 9121 | graph reallocs = 0 / 0 (same size) / (changed size) 57.26.238.595 I slot release: id 1 | task 9121 | stop processing: n_tokens = 846, truncated = 0 57.26.238.606 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 323, progress = 0.38, t = 15.94 s / 20.26 tokens per second 57.26.245.034 I slot print_timing: id 2 | task 9127 | prompt processing, n_tokens = 394, progress = 0.43, t = 15.94 s / 24.72 tokens per second 57.26.249.760 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 385, progress = 0.43, t = 15.94 s / 24.16 tokens per second 57.38.479.989 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 57.38.480.063 I slot launch_slot_: id 1 | task 9133 | processing task, is_child = 0 57.38.480.073 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 723, progress = 0.86, t = 28.18 s / 25.65 tokens per second 57.38.782.157 I slot print_timing: id 2 | task 9127 | prompt processing, n_tokens = 723, progress = 0.79, t = 28.18 s / 25.66 tokens per second 57.38.786.526 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 723, progress = 0.80, t = 28.18 s / 25.66 tokens per second 57.46.150.697 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 835, progress = 1.00, t = 35.85 s / 23.29 tokens per second 57.46.445.383 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 135, progress = 1.00, t = 7.38 s / 18.30 tokens per second 57.46.450.268 I slot print_timing: id 2 | task 9127 | prompt processing, n_tokens = 906, progress = 1.00, t = 35.85 s / 25.27 tokens per second 57.46.463.776 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 897, progress = 1.00, t = 35.85 s / 25.02 tokens per second 57.47.055.395 I slot print_timing: id 0 | task 9126 | prompt eval time = 36547.31 ms / 839 tokens ( 43.56 ms per token, 22.96 tokens per second) 57.47.055.397 I slot print_timing: id 0 | task 9126 | eval time = 211.29 ms / 2 tokens ( 211.29 ms per token, 4.73 tokens per second) 57.47.055.398 I slot print_timing: id 0 | task 9126 | total time = 36758.60 ms / 841 tokens 57.47.055.398 I slot print_timing: id 0 | task 9126 | graphs reused = 7886 57.47.055.399 I slot print_timing: id 0 | task 9126 | graph reallocs = 0 / 0 (same size) / (changed size) 57.47.055.436 I slot release: id 0 | task 9126 | stop processing: n_tokens = 840, truncated = 0 57.47.055.597 I slot print_timing: id 1 | task 9133 | prompt eval time = 8069.64 ms / 139 tokens ( 58.05 ms per token, 17.23 tokens per second) 57.47.055.599 I slot print_timing: id 1 | task 9133 | eval time = 211.34 ms / 2 tokens ( 211.34 ms per token, 4.73 tokens per second) 57.47.055.600 I slot print_timing: id 1 | task 9133 | total time = 8280.98 ms / 141 tokens 57.47.055.600 I slot print_timing: id 1 | task 9133 | graphs reused = 7886 57.47.055.600 I slot print_timing: id 1 | task 9133 | graph reallocs = 0 / 0 (same size) / (changed size) 57.47.055.624 I slot release: id 1 | task 9133 | stop processing: n_tokens = 863, truncated = 0 57.47.055.777 I slot print_timing: id 2 | task 9127 | prompt eval time = 36543.15 ms / 910 tokens ( 40.16 ms per token, 24.90 tokens per second) 57.47.055.778 I slot print_timing: id 2 | task 9127 | eval time = 211.35 ms / 2 tokens ( 211.35 ms per token, 4.73 tokens per second) 57.47.055.779 I slot print_timing: id 2 | task 9127 | total time = 36754.50 ms / 912 tokens 57.47.055.779 I slot print_timing: id 2 | task 9127 | graphs reused = 7886 57.47.055.780 I slot print_timing: id 2 | task 9127 | graph reallocs = 0 / 0 (same size) / (changed size) 57.47.055.805 I slot release: id 2 | task 9127 | stop processing: n_tokens = 911, truncated = 0 57.47.055.980 I slot print_timing: id 3 | task 9128 | prompt eval time = 36543.47 ms / 901 tokens ( 40.56 ms per token, 24.66 tokens per second) 57.47.055.982 I slot print_timing: id 3 | task 9128 | eval time = 211.17 ms / 2 tokens ( 211.17 ms per token, 4.74 tokens per second) 57.47.055.983 I slot print_timing: id 3 | task 9128 | total time = 36754.64 ms / 903 tokens 57.47.055.983 I slot print_timing: id 3 | task 9128 | graphs reused = 7886 57.47.055.983 I slot print_timing: id 3 | task 9128 | graph reallocs = 0 / 0 (same size) / (changed size) 57.47.056.002 I slot release: id 3 | task 9128 | stop processing: n_tokens = 902, truncated = 0 57.47.065.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 82262797241 57.47.065.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.547 MiB) 57.47.084.748 I slot launch_slot_: id 0 | task 9137 | processing task, is_child = 0 57.47.084.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.585 MiB) 57.47.103.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.961 MiB) 57.47.121.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 57.47.140.972 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 82262797429 57.47.141.076 I slot launch_slot_: id 1 | task 9138 | processing task, is_child = 0 57.47.141.176 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 82262797610 57.47.141.237 I slot launch_slot_: id 2 | task 9139 | processing task, is_child = 0 57.47.141.286 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 82262797807 57.47.141.349 I slot launch_slot_: id 3 | task 9140 | processing task, is_child = 0 57.52.742.477 I slot print_timing: id 0 | task 9137 | prompt processing, n_tokens = 124, progress = 0.18, t = 5.60 s / 22.14 tokens per second 57.52.912.538 I slot print_timing: id 1 | task 9138 | prompt processing, n_tokens = 122, progress = 0.16, t = 5.60 s / 21.78 tokens per second 57.52.917.372 I slot print_timing: id 2 | task 9139 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.60 s / 21.25 tokens per second 57.52.922.257 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.60 s / 21.25 tokens per second 57.58.046.307 I slot print_timing: id 0 | task 9137 | prompt processing, n_tokens = 172, progress = 0.25, t = 10.90 s / 15.77 tokens per second 57.58.222.830 I slot print_timing: id 1 | task 9138 | prompt processing, n_tokens = 253, progress = 0.33, t = 10.90 s / 23.20 tokens per second 57.58.227.240 I slot print_timing: id 2 | task 9139 | prompt processing, n_tokens = 246, progress = 0.30, t = 10.90 s / 22.56 tokens per second 57.58.227.249 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 246, progress = 0.29, t = 10.90 s / 22.56 tokens per second 58.08.727.769 I slot print_timing: id 0 | task 9137 | prompt processing, n_tokens = 583, progress = 0.85, t = 21.59 s / 27.01 tokens per second 58.09.159.144 I slot print_timing: id 1 | task 9138 | prompt processing, n_tokens = 632, progress = 0.82, t = 21.59 s / 29.28 tokens per second 58.09.163.574 I slot print_timing: id 2 | task 9139 | prompt processing, n_tokens = 309, progress = 0.37, t = 21.59 s / 14.31 tokens per second 58.09.168.011 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 335, progress = 0.39, t = 21.59 s / 15.52 tokens per second 58.20.443.589 I slot print_timing: id 0 | task 9137 | prompt processing, n_tokens = 684, progress = 0.99, t = 33.30 s / 20.54 tokens per second 58.20.877.157 I slot print_timing: id 1 | task 9138 | prompt processing, n_tokens = 765, progress = 0.99, t = 33.30 s / 22.97 tokens per second 58.20.881.824 I slot print_timing: id 2 | task 9139 | prompt processing, n_tokens = 708, progress = 0.86, t = 33.30 s / 21.26 tokens per second 58.20.886.357 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 708, progress = 0.83, t = 33.30 s / 21.26 tokens per second 58.24.273.113 I slot print_timing: id 2 | task 9139 | prompt processing, n_tokens = 821, progress = 1.00, t = 37.13 s / 22.11 tokens per second 58.24.281.255 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 847, progress = 1.00, t = 37.13 s / 22.81 tokens per second 58.24.699.236 I slot print_timing: id 0 | task 9137 | prompt eval time = 37131.52 ms / 688 tokens ( 53.97 ms per token, 18.53 tokens per second) 58.24.699.238 I slot print_timing: id 0 | task 9137 | eval time = 426.36 ms / 2 tokens ( 426.36 ms per token, 2.35 tokens per second) 58.24.699.239 I slot print_timing: id 0 | task 9137 | total time = 37557.88 ms / 690 tokens 58.24.699.239 I slot print_timing: id 0 | task 9137 | graphs reused = 7886 58.24.699.239 I slot print_timing: id 0 | task 9137 | graph reallocs = 0 / 0 (same size) / (changed size) 58.24.699.273 I slot release: id 0 | task 9137 | stop processing: n_tokens = 689, truncated = 0 58.24.699.408 I slot print_timing: id 1 | task 9138 | prompt eval time = 37131.68 ms / 769 tokens ( 48.29 ms per token, 20.71 tokens per second) 58.24.699.414 I slot print_timing: id 1 | task 9138 | eval time = 426.31 ms / 2 tokens ( 426.31 ms per token, 2.35 tokens per second) 58.24.699.415 I slot print_timing: id 1 | task 9138 | total time = 37557.99 ms / 771 tokens 58.24.699.415 I slot print_timing: id 1 | task 9138 | graphs reused = 7886 58.24.699.416 I slot print_timing: id 1 | task 9138 | graph reallocs = 0 / 0 (same size) / (changed size) 58.24.699.441 I slot release: id 1 | task 9138 | stop processing: n_tokens = 770, truncated = 0 58.24.884.651 I slot print_timing: id 2 | task 9139 | prompt eval time = 37558.20 ms / 825 tokens ( 45.53 ms per token, 21.97 tokens per second) 58.24.884.657 I slot print_timing: id 2 | task 9139 | eval time = 184.97 ms / 2 tokens ( 184.97 ms per token, 5.41 tokens per second) 58.24.884.657 I slot print_timing: id 2 | task 9139 | total time = 37743.17 ms / 827 tokens 58.24.884.658 I slot print_timing: id 2 | task 9139 | graphs reused = 7886 58.24.884.658 I slot print_timing: id 2 | task 9139 | graph reallocs = 0 / 0 (same size) / (changed size) 58.24.884.694 I slot release: id 2 | task 9139 | stop processing: n_tokens = 826, truncated = 0 58.24.884.906 I slot print_timing: id 3 | task 9140 | prompt eval time = 37558.37 ms / 851 tokens ( 44.13 ms per token, 22.66 tokens per second) 58.24.884.908 I slot print_timing: id 3 | task 9140 | eval time = 184.99 ms / 2 tokens ( 184.99 ms per token, 5.41 tokens per second) 58.24.884.909 I slot print_timing: id 3 | task 9140 | total time = 37743.36 ms / 853 tokens 58.24.884.909 I slot print_timing: id 3 | task 9140 | graphs reused = 7886 58.24.884.909 I slot print_timing: id 3 | task 9140 | graph reallocs = 0 / 0 (same size) / (changed size) 58.24.884.937 I slot release: id 3 | task 9140 | stop processing: n_tokens = 852, truncated = 0 58.24.884.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.857 58.24.884.969 I slot launch_slot_: id 1 | task 9148 | processing task, is_child = 0 58.24.885.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 58.24.909.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.773 MiB) 58.24.928.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 58.24.947.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 82300441078 58.24.948.002 I slot launch_slot_: id 0 | task 9149 | processing task, is_child = 0 58.24.948.093 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 82300626499 58.24.948.160 I slot launch_slot_: id 2 | task 9150 | processing task, is_child = 0 58.24.948.204 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 82300626742 58.24.948.263 I slot launch_slot_: id 3 | task 9151 | processing task, is_child = 0 58.30.017.881 I slot print_timing: id 0 | task 9149 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.07 s / 20.71 tokens per second 58.30.318.245 I slot print_timing: id 1 | task 9148 | prompt processing, n_tokens = 116, progress = 0.99, t = 5.07 s / 22.88 tokens per second 58.30.322.752 I slot print_timing: id 2 | task 9150 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.06 s / 20.75 tokens per second 58.30.327.161 I slot print_timing: id 3 | task 9151 | prompt processing, n_tokens = 105, progress = 0.14, t = 5.06 s / 20.75 tokens per second 58.34.437.673 I slot print_timing: id 0 | task 9149 | prompt processing, n_tokens = 197, progress = 0.28, t = 9.49 s / 20.76 tokens per second 58.34.445.026 I slot print_timing: id 2 | task 9150 | prompt processing, n_tokens = 203, progress = 0.28, t = 9.48 s / 21.41 tokens per second 58.34.449.475 I slot print_timing: id 3 | task 9151 | prompt processing, n_tokens = 220, progress = 0.30, t = 9.48 s / 23.21 tokens per second 58.48.324.769 I slot print_timing: id 1 | task 9148 | prompt eval time = 9489.32 ms / 120 tokens ( 79.08 ms per token, 12.65 tokens per second) 58.48.324.773 I slot print_timing: id 1 | task 9148 | eval time = 13887.10 ms / 2 tokens (13887.10 ms per token, 0.07 tokens per second) 58.48.324.777 I slot print_timing: id 1 | task 9148 | total time = 23376.42 ms / 122 tokens 58.48.324.779 I slot print_timing: id 1 | task 9148 | graphs reused = 7886 58.48.324.779 I slot print_timing: id 1 | task 9148 | graph reallocs = 0 / 0 (same size) / (changed size) 58.48.324.814 I slot release: id 1 | task 9148 | stop processing: n_tokens = 753, truncated = 0 58.48.324.828 I slot print_timing: id 0 | task 9149 | prompt processing, n_tokens = 603, progress = 0.85, t = 23.38 s / 25.80 tokens per second 58.48.330.907 I slot print_timing: id 2 | task 9150 | prompt processing, n_tokens = 603, progress = 0.84, t = 23.37 s / 25.80 tokens per second 58.48.335.745 I slot print_timing: id 3 | task 9151 | prompt processing, n_tokens = 603, progress = 0.82, t = 23.37 s / 25.80 tokens per second 58.52.372.693 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 82324066619 58.52.372.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.775 MiB) 58.52.803.706 I slot launch_slot_: id 1 | task 9156 | processing task, is_child = 0 58.52.803.722 I slot print_timing: id 0 | task 9149 | prompt processing, n_tokens = 709, progress = 0.99, t = 27.42 s / 25.85 tokens per second 58.52.808.372 I slot print_timing: id 2 | task 9150 | prompt processing, n_tokens = 715, progress = 0.99, t = 27.42 s / 26.08 tokens per second 58.52.813.312 I slot print_timing: id 3 | task 9151 | prompt processing, n_tokens = 732, progress = 0.99, t = 27.42 s / 26.70 tokens per second 58.56.144.557 I slot print_timing: id 0 | task 9149 | prompt eval time = 29688.69 ms / 713 tokens ( 41.64 ms per token, 24.02 tokens per second) 58.56.144.562 I slot print_timing: id 0 | task 9149 | eval time = 1507.59 ms / 2 tokens ( 1507.59 ms per token, 0.66 tokens per second) 58.56.144.563 I slot print_timing: id 0 | task 9149 | total time = 31196.28 ms / 715 tokens 58.56.144.563 I slot print_timing: id 0 | task 9149 | graphs reused = 7886 58.56.144.564 I slot print_timing: id 0 | task 9149 | graph reallocs = 0 / 0 (same size) / (changed size) 58.56.144.600 I slot release: id 0 | task 9149 | stop processing: n_tokens = 714, truncated = 0 58.56.144.765 I slot print_timing: id 2 | task 9150 | prompt eval time = 29680.46 ms / 719 tokens ( 41.28 ms per token, 24.22 tokens per second) 58.56.144.767 I slot print_timing: id 2 | task 9150 | eval time = 1507.59 ms / 2 tokens ( 1507.59 ms per token, 0.66 tokens per second) 58.56.144.768 I slot print_timing: id 2 | task 9150 | total time = 31188.04 ms / 721 tokens 58.56.144.768 I slot print_timing: id 2 | task 9150 | graphs reused = 7886 58.56.144.768 I slot print_timing: id 2 | task 9150 | graph reallocs = 0 / 0 (same size) / (changed size) 58.56.144.791 I slot release: id 2 | task 9150 | stop processing: n_tokens = 720, truncated = 0 58.56.144.967 I slot print_timing: id 3 | task 9151 | prompt eval time = 29680.59 ms / 736 tokens ( 40.33 ms per token, 24.80 tokens per second) 58.56.144.972 I slot print_timing: id 3 | task 9151 | eval time = 1507.59 ms / 2 tokens ( 1507.59 ms per token, 0.66 tokens per second) 58.56.144.972 I slot print_timing: id 3 | task 9151 | total time = 31188.18 ms / 738 tokens 58.56.144.972 I slot print_timing: id 3 | task 9151 | graphs reused = 7886 58.56.144.973 I slot print_timing: id 3 | task 9151 | graph reallocs = 0 / 0 (same size) / (changed size) 58.56.144.998 I slot release: id 3 | task 9151 | stop processing: n_tokens = 737, truncated = 0 58.56.145.006 I slot print_timing: id 1 | task 9156 | prompt processing, n_tokens = 194, progress = 0.27, t = 3.34 s / 58.15 tokens per second 58.56.157.219 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.884 58.56.157.256 I slot launch_slot_: id 0 | task 9160 | processing task, is_child = 0 58.56.157.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 59.00.833.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.342 MiB) 59.00.851.575 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.876 59.00.851.651 I slot launch_slot_: id 2 | task 9161 | processing task, is_child = 0 59.00.851.696 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 59.00.851.729 I slot launch_slot_: id 3 | task 9162 | processing task, is_child = 0 59.00.859.346 I slot print_timing: id 1 | task 9156 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.35 s / 180.06 tokens per second 59.05.915.707 I slot print_timing: id 0 | task 9160 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.06 s / 20.14 tokens per second 59.06.099.307 I slot print_timing: id 1 | task 9156 | prompt processing, n_tokens = 706, progress = 0.99, t = 13.11 s / 53.86 tokens per second 59.06.104.443 I slot print_timing: id 2 | task 9161 | prompt processing, n_tokens = 100, progress = 0.99, t = 5.05 s / 19.79 tokens per second 59.06.108.941 I slot print_timing: id 3 | task 9162 | prompt processing, n_tokens = 108, progress = 0.99, t = 5.04 s / 21.41 tokens per second 59.06.699.835 I slot print_timing: id 0 | task 9160 | prompt eval time = 5637.02 ms / 106 tokens ( 53.18 ms per token, 18.80 tokens per second) 59.06.699.841 I slot print_timing: id 0 | task 9160 | eval time = 211.07 ms / 2 tokens ( 211.07 ms per token, 4.74 tokens per second) 59.06.699.841 I slot print_timing: id 0 | task 9160 | total time = 5848.09 ms / 108 tokens 59.06.699.842 I slot print_timing: id 0 | task 9160 | graphs reused = 7886 59.06.699.842 I slot print_timing: id 0 | task 9160 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.699.874 I slot release: id 0 | task 9160 | stop processing: n_tokens = 710, truncated = 0 59.06.700.018 I slot print_timing: id 1 | task 9156 | prompt eval time = 13680.60 ms / 710 tokens ( 19.27 ms per token, 51.90 tokens per second) 59.06.700.020 I slot print_timing: id 1 | task 9156 | eval time = 211.10 ms / 2 tokens ( 211.10 ms per token, 4.74 tokens per second) 59.06.700.022 I slot print_timing: id 1 | task 9156 | total time = 13891.70 ms / 712 tokens 59.06.700.022 I slot print_timing: id 1 | task 9156 | graphs reused = 7886 59.06.700.022 I slot print_timing: id 1 | task 9156 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.700.044 I slot release: id 1 | task 9156 | stop processing: n_tokens = 711, truncated = 0 59.06.700.213 I slot print_timing: id 2 | task 9161 | prompt eval time = 5625.31 ms / 104 tokens ( 54.09 ms per token, 18.49 tokens per second) 59.06.700.215 I slot print_timing: id 2 | task 9161 | eval time = 211.13 ms / 2 tokens ( 211.13 ms per token, 4.74 tokens per second) 59.06.700.216 I slot print_timing: id 2 | task 9161 | total time = 5836.44 ms / 106 tokens 59.06.700.220 I slot print_timing: id 2 | task 9161 | graphs reused = 7886 59.06.700.221 I slot print_timing: id 2 | task 9161 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.700.252 I slot release: id 2 | task 9161 | stop processing: n_tokens = 708, truncated = 0 59.06.700.411 I slot print_timing: id 3 | task 9162 | prompt eval time = 5617.99 ms / 112 tokens ( 50.16 ms per token, 19.94 tokens per second) 59.06.700.414 I slot print_timing: id 3 | task 9162 | eval time = 211.12 ms / 2 tokens ( 211.12 ms per token, 4.74 tokens per second) 59.06.700.414 I slot print_timing: id 3 | task 9162 | total time = 5829.11 ms / 114 tokens 59.06.700.414 I slot print_timing: id 3 | task 9162 | graphs reused = 7886 59.06.700.415 I slot print_timing: id 3 | task 9162 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.700.431 I slot release: id 3 | task 9162 | stop processing: n_tokens = 716, truncated = 0 59.06.710.236 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.889 59.06.710.266 I slot launch_slot_: id 0 | task 9166 | processing task, is_child = 0 59.06.710.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 800.650 MiB) 59.06.728.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.088 MiB) 59.06.746.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.089 MiB) 59.06.765.079 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.890 59.06.765.138 I slot launch_slot_: id 1 | task 9167 | processing task, is_child = 0 59.06.765.221 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 59.06.765.241 I slot launch_slot_: id 2 | task 9168 | processing task, is_child = 0 59.06.765.279 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.881 59.06.765.299 I slot launch_slot_: id 3 | task 9169 | processing task, is_child = 0 59.12.103.265 I slot print_timing: id 0 | task 9166 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.34 s / 19.11 tokens per second 59.12.863.718 I slot print_timing: id 1 | task 9167 | prompt processing, n_tokens = 110, progress = 0.99, t = 5.33 s / 20.64 tokens per second 59.12.868.209 I slot print_timing: id 2 | task 9168 | prompt processing, n_tokens = 109, progress = 0.99, t = 5.32 s / 20.48 tokens per second 59.12.872.700 I slot print_timing: id 3 | task 9169 | prompt processing, n_tokens = 144, progress = 0.99, t = 5.32 s / 27.09 tokens per second 59.13.454.380 I slot print_timing: id 0 | task 9166 | prompt eval time = 6477.27 ms / 106 tokens ( 61.11 ms per token, 16.36 tokens per second) 59.13.454.385 I slot print_timing: id 0 | task 9166 | eval time = 211.80 ms / 2 tokens ( 211.80 ms per token, 4.72 tokens per second) 59.13.454.385 I slot print_timing: id 0 | task 9166 | total time = 6689.07 ms / 108 tokens 59.13.454.386 I slot print_timing: id 0 | task 9166 | graphs reused = 7886 59.13.454.386 I slot print_timing: id 0 | task 9166 | graph reallocs = 0 / 0 (same size) / (changed size) 59.13.454.419 I slot release: id 0 | task 9166 | stop processing: n_tokens = 710, truncated = 0 59.13.454.566 I slot print_timing: id 1 | task 9167 | prompt eval time = 6469.82 ms / 114 tokens ( 56.75 ms per token, 17.62 tokens per second) 59.13.454.572 I slot print_timing: id 1 | task 9167 | eval time = 211.79 ms / 2 tokens ( 211.79 ms per token, 4.72 tokens per second) 59.13.454.572 I slot print_timing: id 1 | task 9167 | total time = 6681.62 ms / 116 tokens 59.13.454.572 I slot print_timing: id 1 | task 9167 | graphs reused = 7886 59.13.454.573 I slot print_timing: id 1 | task 9167 | graph reallocs = 0 / 0 (same size) / (changed size) 59.13.454.599 I slot release: id 1 | task 9167 | stop processing: n_tokens = 718, truncated = 0 59.13.454.761 I slot print_timing: id 2 | task 9168 | prompt eval time = 6462.53 ms / 113 tokens ( 57.19 ms per token, 17.49 tokens per second) 59.13.454.767 I slot print_timing: id 2 | task 9168 | eval time = 211.79 ms / 2 tokens ( 211.79 ms per token, 4.72 tokens per second) 59.13.454.767 I slot print_timing: id 2 | task 9168 | total time = 6674.32 ms / 115 tokens 59.13.454.767 I slot print_timing: id 2 | task 9168 | graphs reused = 7886 59.13.454.768 I slot print_timing: id 2 | task 9168 | graph reallocs = 0 / 0 (same size) / (changed size) 59.13.454.784 I slot release: id 2 | task 9168 | stop processing: n_tokens = 717, truncated = 0 59.13.454.960 I slot print_timing: id 3 | task 9169 | prompt eval time = 6455.18 ms / 148 tokens ( 43.62 ms per token, 22.93 tokens per second) 59.13.454.963 I slot print_timing: id 3 | task 9169 | eval time = 211.78 ms / 2 tokens ( 211.78 ms per token, 4.72 tokens per second) 59.13.454.963 I slot print_timing: id 3 | task 9169 | total time = 6666.96 ms / 150 tokens 59.13.454.963 I slot print_timing: id 3 | task 9169 | graphs reused = 7886 59.13.454.964 I slot print_timing: id 3 | task 9169 | graph reallocs = 0 / 0 (same size) / (changed size) 59.13.454.980 I slot release: id 3 | task 9169 | stop processing: n_tokens = 752, truncated = 0 59.13.464.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 82349196224 59.13.464.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.527 MiB) 59.13.483.887 I slot launch_slot_: id 0 | task 9173 | processing task, is_child = 0 59.13.483.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 791.209 MiB) 59.13.502.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 59.13.520.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.401 MiB) 59.13.538.805 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 82349196404 59.13.538.904 I slot launch_slot_: id 1 | task 9174 | processing task, is_child = 0 59.13.538.992 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 82349196589 59.13.539.058 I slot launch_slot_: id 2 | task 9175 | processing task, is_child = 0 59.13.539.100 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 82349196785 59.13.539.159 I slot launch_slot_: id 3 | task 9176 | processing task, is_child = 0 59.21.785.391 I slot print_timing: id 0 | task 9173 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.25 s / 22.19 tokens per second 59.21.980.125 I slot print_timing: id 1 | task 9174 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.25 s / 22.19 tokens per second 59.21.984.796 I slot print_timing: id 2 | task 9175 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.25 s / 21.83 tokens per second 59.21.989.672 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.25 s / 21.83 tokens per second 59.27.404.624 I slot print_timing: id 0 | task 9173 | prompt processing, n_tokens = 364, progress = 0.34, t = 13.87 s / 26.25 tokens per second 59.27.404.638 I slot print_timing: id 1 | task 9174 | prompt processing, n_tokens = 364, progress = 0.33, t = 13.87 s / 26.25 tokens per second 59.27.404.647 I slot print_timing: id 2 | task 9175 | prompt processing, n_tokens = 296, progress = 0.34, t = 13.87 s / 21.35 tokens per second 59.27.404.652 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 296, progress = 0.33, t = 13.87 s / 21.35 tokens per second 59.36.128.358 I slot print_timing: id 0 | task 9173 | prompt processing, n_tokens = 566, progress = 0.52, t = 22.59 s / 25.06 tokens per second 59.36.439.715 I slot print_timing: id 1 | task 9174 | prompt processing, n_tokens = 575, progress = 0.53, t = 22.59 s / 25.45 tokens per second 59.36.444.130 I slot print_timing: id 2 | task 9175 | prompt processing, n_tokens = 364, progress = 0.41, t = 22.59 s / 16.11 tokens per second 59.36.448.535 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 380, progress = 0.42, t = 22.59 s / 16.82 tokens per second 59.53.305.878 I slot print_timing: id 0 | task 9173 | prompt processing, n_tokens = 905, progress = 0.84, t = 39.77 s / 22.76 tokens per second 59.53.619.058 I slot print_timing: id 1 | task 9174 | prompt processing, n_tokens = 905, progress = 0.83, t = 39.77 s / 22.76 tokens per second 59.53.623.484 I slot print_timing: id 2 | task 9175 | prompt processing, n_tokens = 762, progress = 0.87, t = 39.77 s / 19.16 tokens per second 59.53.627.900 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 762, progress = 0.85, t = 39.77 s / 19.16 tokens per second 60.00.859.725 I slot print_timing: id 0 | task 9173 | prompt processing, n_tokens = 1078, progress = 1.00, t = 47.32 s / 22.78 tokens per second 60.01.171.392 I slot print_timing: id 1 | task 9174 | prompt processing, n_tokens = 1087, progress = 1.00, t = 47.32 s / 22.97 tokens per second 60.01.176.163 I slot print_timing: id 2 | task 9175 | prompt processing, n_tokens = 876, progress = 1.00, t = 47.32 s / 18.51 tokens per second 60.01.180.684 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 892, progress = 1.00, t = 47.32 s / 18.85 tokens per second 60.01.764.392 I slot print_timing: id 0 | task 9173 | prompt eval time = 48013.48 ms / 1082 tokens ( 44.37 ms per token, 22.54 tokens per second) 60.01.764.398 I slot print_timing: id 0 | task 9173 | eval time = 211.74 ms / 2 tokens ( 211.74 ms per token, 4.72 tokens per second) 60.01.764.398 I slot print_timing: id 0 | task 9173 | total time = 48225.22 ms / 1084 tokens 60.01.764.399 I slot print_timing: id 0 | task 9173 | graphs reused = 7886 60.01.764.399 I slot print_timing: id 0 | task 9173 | graph reallocs = 0 / 0 (same size) / (changed size) 60.01.764.438 I slot release: id 0 | task 9173 | stop processing: n_tokens = 1083, truncated = 0 60.01.764.588 I slot print_timing: id 1 | task 9174 | prompt eval time = 48013.62 ms / 1091 tokens ( 44.01 ms per token, 22.72 tokens per second) 60.01.764.590 I slot print_timing: id 1 | task 9174 | eval time = 211.74 ms / 2 tokens ( 211.74 ms per token, 4.72 tokens per second) 60.01.764.591 I slot print_timing: id 1 | task 9174 | total time = 48225.36 ms / 1093 tokens 60.01.764.591 I slot print_timing: id 1 | task 9174 | graphs reused = 7886 60.01.764.591 I slot print_timing: id 1 | task 9174 | graph reallocs = 0 / 0 (same size) / (changed size) 60.01.764.618 I slot release: id 1 | task 9174 | stop processing: n_tokens = 1092, truncated = 0 60.01.764.788 I slot print_timing: id 2 | task 9175 | prompt eval time = 48013.77 ms / 880 tokens ( 54.56 ms per token, 18.33 tokens per second) 60.01.764.792 I slot print_timing: id 2 | task 9175 | eval time = 211.73 ms / 2 tokens ( 211.73 ms per token, 4.72 tokens per second) 60.01.764.792 I slot print_timing: id 2 | task 9175 | total time = 48225.50 ms / 882 tokens 60.01.764.792 I slot print_timing: id 2 | task 9175 | graphs reused = 7886 60.01.764.793 I slot print_timing: id 2 | task 9175 | graph reallocs = 0 / 0 (same size) / (changed size) 60.01.764.820 I slot release: id 2 | task 9175 | stop processing: n_tokens = 881, truncated = 0 60.01.765.016 I slot print_timing: id 3 | task 9176 | prompt eval time = 48013.93 ms / 896 tokens ( 53.59 ms per token, 18.66 tokens per second) 60.01.765.018 I slot print_timing: id 3 | task 9176 | eval time = 211.75 ms / 2 tokens ( 211.75 ms per token, 4.72 tokens per second) 60.01.765.019 I slot print_timing: id 3 | task 9176 | total time = 48225.68 ms / 898 tokens 60.01.765.020 I slot print_timing: id 3 | task 9176 | graphs reused = 7886 60.01.765.020 I slot print_timing: id 3 | task 9176 | graph reallocs = 0 / 0 (same size) / (changed size) 60.01.765.040 I slot release: id 3 | task 9176 | stop processing: n_tokens = 897, truncated = 0 60.01.774.950 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 60.01.774.977 I slot launch_slot_: id 1 | task 9184 | processing task, is_child = 0 60.01.775.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.211 MiB) 60.01.795.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 60.01.813.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 60.01.832.721 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.901 60.01.832.779 I slot launch_slot_: id 0 | task 9185 | processing task, is_child = 0 60.01.832.867 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 82397506625 60.01.837.726 I slot launch_slot_: id 2 | task 9186 | processing task, is_child = 0 60.01.837.782 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 82397506845 60.01.837.850 I slot launch_slot_: id 3 | task 9187 | processing task, is_child = 0 60.10.114.774 I slot print_timing: id 0 | task 9185 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.28 s / 20.66 tokens per second 60.10.415.613 I slot print_timing: id 1 | task 9184 | prompt processing, n_tokens = 162, progress = 1.00, t = 8.27 s / 19.59 tokens per second 60.10.420.145 I slot print_timing: id 2 | task 9186 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.26 s / 20.58 tokens per second 60.10.424.670 I slot print_timing: id 3 | task 9187 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.25 s / 22.17 tokens per second 60.12.971.126 I slot print_timing: id 3 | task 9187 | prompt processing, n_tokens = 364, progress = 0.34, t = 11.11 s / 32.76 tokens per second 60.15.726.624 I slot print_timing: id 0 | task 9185 | prompt eval time = 11132.81 ms / 175 tokens ( 63.62 ms per token, 15.72 tokens per second) 60.15.726.627 I slot print_timing: id 0 | task 9185 | eval time = 2755.95 ms / 2 tokens ( 2755.95 ms per token, 0.36 tokens per second) 60.15.726.627 I slot print_timing: id 0 | task 9185 | total time = 13888.76 ms / 177 tokens 60.15.726.628 I slot print_timing: id 0 | task 9185 | graphs reused = 7886 60.15.726.628 I slot print_timing: id 0 | task 9185 | graph reallocs = 0 / 0 (same size) / (changed size) 60.15.726.672 I slot release: id 0 | task 9185 | stop processing: n_tokens = 1081, truncated = 0 60.15.726.907 I slot print_timing: id 1 | task 9184 | prompt eval time = 11125.54 ms / 166 tokens ( 67.02 ms per token, 14.92 tokens per second) 60.15.726.914 I slot print_timing: id 1 | task 9184 | eval time = 2756.00 ms / 2 tokens ( 2756.00 ms per token, 0.36 tokens per second) 60.15.726.915 I slot print_timing: id 1 | task 9184 | total time = 13881.54 ms / 168 tokens 60.15.726.915 I slot print_timing: id 1 | task 9184 | graphs reused = 7886 60.15.726.916 I slot print_timing: id 1 | task 9184 | graph reallocs = 0 / 0 (same size) / (changed size) 60.15.726.944 I slot release: id 1 | task 9184 | stop processing: n_tokens = 1072, truncated = 0 60.15.727.171 I slot print_timing: id 2 | task 9186 | prompt eval time = 11118.21 ms / 174 tokens ( 63.90 ms per token, 15.65 tokens per second) 60.15.727.174 I slot print_timing: id 2 | task 9186 | eval time = 2756.05 ms / 2 tokens ( 2756.05 ms per token, 0.36 tokens per second) 60.15.727.174 I slot print_timing: id 2 | task 9186 | total time = 13874.26 ms / 176 tokens 60.15.727.174 I slot print_timing: id 2 | task 9186 | graphs reused = 7886 60.15.727.174 I slot print_timing: id 2 | task 9186 | graph reallocs = 0 / 0 (same size) / (changed size) 60.15.727.197 I slot release: id 2 | task 9186 | stop processing: n_tokens = 1080, truncated = 0 60.15.727.205 I slot print_timing: id 3 | task 9187 | prompt processing, n_tokens = 569, progress = 0.52, t = 13.87 s / 41.04 tokens per second 60.15.739.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.904 60.15.739.943 I slot launch_slot_: id 0 | task 9192 | processing task, is_child = 0 60.19.723.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 60.19.742.685 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.911 60.19.742.753 I slot launch_slot_: id 1 | task 9193 | processing task, is_child = 0 60.19.742.809 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.905 60.19.742.834 I slot launch_slot_: id 2 | task 9194 | processing task, is_child = 0 60.19.765.529 I slot print_timing: id 3 | task 9187 | prompt processing, n_tokens = 905, progress = 0.83, t = 13.88 s / 65.20 tokens per second 60.28.162.734 I slot print_timing: id 0 | task 9192 | prompt processing, n_tokens = 173, progress = 1.00, t = 8.42 s / 20.55 tokens per second 60.28.336.923 I slot print_timing: id 1 | task 9193 | prompt processing, n_tokens = 164, progress = 1.00, t = 8.41 s / 19.50 tokens per second 60.28.341.440 I slot print_timing: id 2 | task 9194 | prompt processing, n_tokens = 179, progress = 1.00, t = 8.40 s / 21.30 tokens per second 60.28.345.970 I slot print_timing: id 3 | task 9187 | prompt processing, n_tokens = 1081, progress = 1.00, t = 26.30 s / 41.10 tokens per second 60.28.930.712 I slot print_timing: id 0 | task 9192 | prompt eval time = 8975.69 ms / 177 tokens ( 50.71 ms per token, 19.72 tokens per second) 60.28.930.715 I slot print_timing: id 0 | task 9192 | eval time = 212.18 ms / 2 tokens ( 212.18 ms per token, 4.71 tokens per second) 60.28.930.716 I slot print_timing: id 0 | task 9192 | total time = 9187.87 ms / 179 tokens 60.28.930.716 I slot print_timing: id 0 | task 9192 | graphs reused = 7886 60.28.930.717 I slot print_timing: id 0 | task 9192 | graph reallocs = 0 / 0 (same size) / (changed size) 60.28.930.755 I slot release: id 0 | task 9192 | stop processing: n_tokens = 1083, truncated = 0 60.28.930.905 I slot print_timing: id 1 | task 9193 | prompt eval time = 8968.22 ms / 168 tokens ( 53.38 ms per token, 18.73 tokens per second) 60.28.930.909 I slot print_timing: id 1 | task 9193 | eval time = 212.22 ms / 2 tokens ( 212.22 ms per token, 4.71 tokens per second) 60.28.930.910 I slot print_timing: id 1 | task 9193 | total time = 9180.44 ms / 170 tokens 60.28.930.911 I slot print_timing: id 1 | task 9193 | graphs reused = 7886 60.28.930.911 I slot print_timing: id 1 | task 9193 | graph reallocs = 0 / 0 (same size) / (changed size) 60.28.930.936 I slot release: id 1 | task 9193 | stop processing: n_tokens = 1074, truncated = 0 60.28.931.098 I slot print_timing: id 2 | task 9194 | prompt eval time = 8960.84 ms / 183 tokens ( 48.97 ms per token, 20.42 tokens per second) 60.28.931.103 I slot print_timing: id 2 | task 9194 | eval time = 212.25 ms / 2 tokens ( 212.25 ms per token, 4.71 tokens per second) 60.28.931.103 I slot print_timing: id 2 | task 9194 | total time = 9173.09 ms / 185 tokens 60.28.931.103 I slot print_timing: id 2 | task 9194 | graphs reused = 7886 60.28.931.104 I slot print_timing: id 2 | task 9194 | graph reallocs = 0 / 0 (same size) / (changed size) 60.28.931.129 I slot release: id 2 | task 9194 | stop processing: n_tokens = 1089, truncated = 0 60.28.931.282 I slot print_timing: id 3 | task 9187 | prompt eval time = 26858.59 ms / 1085 tokens ( 24.75 ms per token, 40.40 tokens per second) 60.28.931.285 I slot print_timing: id 3 | task 9187 | eval time = 212.21 ms / 2 tokens ( 212.21 ms per token, 4.71 tokens per second) 60.28.931.285 I slot print_timing: id 3 | task 9187 | total time = 27070.81 ms / 1087 tokens 60.28.931.285 I slot print_timing: id 3 | task 9187 | graphs reused = 7886 60.28.931.286 I slot print_timing: id 3 | task 9187 | graph reallocs = 0 / 0 (same size) / (changed size) 60.28.931.305 I slot release: id 3 | task 9187 | stop processing: n_tokens = 1086, truncated = 0 60.28.940.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.902 60.28.940.463 I slot launch_slot_: id 0 | task 9198 | processing task, is_child = 0 60.28.940.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.397 MiB) 60.28.960.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.897 MiB) 60.28.992.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 60.29.011.780 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.910 60.29.011.832 I slot launch_slot_: id 1 | task 9199 | processing task, is_child = 0 60.29.011.939 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.897 60.29.011.960 I slot launch_slot_: id 2 | task 9200 | processing task, is_child = 0 60.29.012.015 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.900 60.29.012.035 I slot launch_slot_: id 3 | task 9201 | processing task, is_child = 0 60.37.056.546 I slot print_timing: id 0 | task 9198 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.04 s / 21.26 tokens per second 60.37.243.666 I slot print_timing: id 1 | task 9199 | prompt processing, n_tokens = 167, progress = 1.00, t = 8.04 s / 20.78 tokens per second 60.37.248.910 I slot print_timing: id 2 | task 9200 | prompt processing, n_tokens = 166, progress = 1.00, t = 8.03 s / 20.67 tokens per second 60.37.254.317 I slot print_timing: id 3 | task 9201 | prompt processing, n_tokens = 174, progress = 1.00, t = 8.02 s / 21.69 tokens per second 60.37.840.459 I slot print_timing: id 0 | task 9198 | prompt eval time = 8616.02 ms / 175 tokens ( 49.23 ms per token, 20.31 tokens per second) 60.37.840.464 I slot print_timing: id 0 | task 9198 | eval time = 212.40 ms / 2 tokens ( 212.40 ms per token, 4.71 tokens per second) 60.37.840.464 I slot print_timing: id 0 | task 9198 | total time = 8828.42 ms / 177 tokens 60.37.840.465 I slot print_timing: id 0 | task 9198 | graphs reused = 7886 60.37.840.465 I slot print_timing: id 0 | task 9198 | graph reallocs = 0 / 0 (same size) / (changed size) 60.37.840.508 I slot release: id 0 | task 9198 | stop processing: n_tokens = 1081, truncated = 0 60.37.840.659 I slot print_timing: id 1 | task 9199 | prompt eval time = 8608.49 ms / 171 tokens ( 50.34 ms per token, 19.86 tokens per second) 60.37.840.661 I slot print_timing: id 1 | task 9199 | eval time = 212.40 ms / 2 tokens ( 212.40 ms per token, 4.71 tokens per second) 60.37.840.661 I slot print_timing: id 1 | task 9199 | total time = 8820.89 ms / 173 tokens 60.37.840.662 I slot print_timing: id 1 | task 9199 | graphs reused = 7886 60.37.840.662 I slot print_timing: id 1 | task 9199 | graph reallocs = 0 / 0 (same size) / (changed size) 60.37.840.686 I slot release: id 1 | task 9199 | stop processing: n_tokens = 1077, truncated = 0 60.37.840.849 I slot print_timing: id 2 | task 9200 | prompt eval time = 8601.16 ms / 170 tokens ( 50.60 ms per token, 19.76 tokens per second) 60.37.840.852 I slot print_timing: id 2 | task 9200 | eval time = 212.39 ms / 2 tokens ( 212.39 ms per token, 4.71 tokens per second) 60.37.840.853 I slot print_timing: id 2 | task 9200 | total time = 8813.55 ms / 172 tokens 60.37.840.853 I slot print_timing: id 2 | task 9200 | graphs reused = 7886 60.37.840.853 I slot print_timing: id 2 | task 9200 | graph reallocs = 0 / 0 (same size) / (changed size) 60.37.840.877 I slot release: id 2 | task 9200 | stop processing: n_tokens = 1076, truncated = 0 60.37.841.046 I slot print_timing: id 3 | task 9201 | prompt eval time = 8593.79 ms / 178 tokens ( 48.28 ms per token, 20.71 tokens per second) 60.37.841.049 I slot print_timing: id 3 | task 9201 | eval time = 212.37 ms / 2 tokens ( 212.37 ms per token, 4.71 tokens per second) 60.37.841.049 I slot print_timing: id 3 | task 9201 | total time = 8806.16 ms / 180 tokens 60.37.841.049 I slot print_timing: id 3 | task 9201 | graphs reused = 7886 60.37.841.049 I slot print_timing: id 3 | task 9201 | graph reallocs = 0 / 0 (same size) / (changed size) 60.37.841.075 I slot release: id 3 | task 9201 | stop processing: n_tokens = 1084, truncated = 0 60.37.850.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 82433582313 60.37.850.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.022 MiB) 60.37.869.935 I slot launch_slot_: id 0 | task 9205 | processing task, is_child = 0 60.37.869.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 60.37.889.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.148 MiB) 60.37.908.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 60.37.940.250 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 60.37.940.303 I slot launch_slot_: id 1 | task 9206 | processing task, is_child = 0 60.37.940.410 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.908 60.37.940.431 I slot launch_slot_: id 2 | task 9207 | processing task, is_child = 0 60.37.940.484 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1084, t_last = 82433582880 60.37.940.560 I slot launch_slot_: id 3 | task 9208 | processing task, is_child = 0 60.46.849.618 I slot print_timing: id 0 | task 9205 | prompt processing, n_tokens = 210, progress = 0.21, t = 8.91 s / 23.57 tokens per second 60.47.610.874 I slot print_timing: id 1 | task 9206 | prompt processing, n_tokens = 169, progress = 1.00, t = 8.91 s / 18.97 tokens per second 60.47.615.962 I slot print_timing: id 2 | task 9207 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.90 s / 19.10 tokens per second 60.47.620.658 I slot print_timing: id 3 | task 9208 | prompt processing, n_tokens = 210, progress = 0.20, t = 8.89 s / 23.61 tokens per second 60.52.348.013 I slot print_timing: id 0 | task 9205 | prompt processing, n_tokens = 393, progress = 0.39, t = 14.41 s / 27.28 tokens per second 60.52.348.024 I slot print_timing: id 3 | task 9208 | prompt processing, n_tokens = 393, progress = 0.38, t = 14.39 s / 27.31 tokens per second 60.55.493.240 I slot print_timing: id 1 | task 9206 | prompt eval time = 14407.12 ms / 173 tokens ( 83.28 ms per token, 12.01 tokens per second) 60.55.493.246 I slot print_timing: id 1 | task 9206 | eval time = 3145.46 ms / 2 tokens ( 3145.46 ms per token, 0.32 tokens per second) 60.55.493.246 I slot print_timing: id 1 | task 9206 | total time = 17552.58 ms / 175 tokens 60.55.493.247 I slot print_timing: id 1 | task 9206 | graphs reused = 7886 60.55.493.247 I slot print_timing: id 1 | task 9206 | graph reallocs = 0 / 0 (same size) / (changed size) 60.55.493.289 I slot release: id 1 | task 9206 | stop processing: n_tokens = 1079, truncated = 0 60.55.493.507 I slot print_timing: id 2 | task 9207 | prompt eval time = 14399.75 ms / 174 tokens ( 82.76 ms per token, 12.08 tokens per second) 60.55.493.515 I slot print_timing: id 2 | task 9207 | eval time = 3145.50 ms / 2 tokens ( 3145.50 ms per token, 0.32 tokens per second) 60.55.493.515 I slot print_timing: id 2 | task 9207 | total time = 17545.25 ms / 176 tokens 60.55.493.515 I slot print_timing: id 2 | task 9207 | graphs reused = 7886 60.55.493.516 I slot print_timing: id 2 | task 9207 | graph reallocs = 0 / 0 (same size) / (changed size) 60.55.493.554 I slot release: id 2 | task 9207 | stop processing: n_tokens = 1080, truncated = 0 60.55.493.561 I slot print_timing: id 0 | task 9205 | prompt processing, n_tokens = 501, progress = 0.49, t = 17.55 s / 28.54 tokens per second 60.55.499.445 I slot print_timing: id 3 | task 9208 | prompt processing, n_tokens = 515, progress = 0.50, t = 17.54 s / 29.37 tokens per second 60.59.823.647 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 82451235094 60.59.823.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 61.04.130.042 I slot launch_slot_: id 1 | task 9213 | processing task, is_child = 0 61.04.130.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 61.04.149.576 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 82451235359 61.04.149.686 I slot launch_slot_: id 2 | task 9214 | processing task, is_child = 0 61.04.149.698 I slot print_timing: id 0 | task 9205 | prompt processing, n_tokens = 878, progress = 0.86, t = 21.88 s / 40.12 tokens per second 61.04.154.260 I slot print_timing: id 3 | task 9208 | prompt processing, n_tokens = 878, progress = 0.85, t = 21.87 s / 40.15 tokens per second 61.11.110.942 I slot print_timing: id 0 | task 9205 | prompt processing, n_tokens = 1013, progress = 1.00, t = 33.17 s / 30.54 tokens per second 61.12.590.439 I slot print_timing: id 1 | task 9213 | prompt processing, n_tokens = 210, progress = 0.20, t = 6.96 s / 30.19 tokens per second 61.12.594.961 I slot print_timing: id 2 | task 9214 | prompt processing, n_tokens = 210, progress = 0.19, t = 6.96 s / 30.19 tokens per second 61.12.599.353 I slot print_timing: id 3 | task 9208 | prompt processing, n_tokens = 1027, progress = 1.00, t = 33.16 s / 30.98 tokens per second 61.17.256.827 I slot print_timing: id 1 | task 9213 | prompt processing, n_tokens = 393, progress = 0.37, t = 13.10 s / 29.99 tokens per second 61.17.256.840 I slot print_timing: id 2 | task 9214 | prompt processing, n_tokens = 393, progress = 0.36, t = 13.10 s / 29.99 tokens per second 61.22.290.191 I slot print_timing: id 0 | task 9205 | prompt eval time = 39316.02 ms / 1017 tokens ( 38.66 ms per token, 25.87 tokens per second) 61.22.290.194 I slot print_timing: id 0 | task 9205 | eval time = 5033.60 ms / 2 tokens ( 5033.60 ms per token, 0.20 tokens per second) 61.22.290.194 I slot print_timing: id 0 | task 9205 | total time = 44349.62 ms / 1019 tokens 61.22.290.195 I slot print_timing: id 0 | task 9205 | graphs reused = 7886 61.22.290.195 I slot print_timing: id 0 | task 9205 | graph reallocs = 0 / 0 (same size) / (changed size) 61.22.290.239 I slot release: id 0 | task 9205 | stop processing: n_tokens = 1018, truncated = 0 61.22.290.439 I slot print_timing: id 3 | task 9208 | prompt eval time = 39301.09 ms / 1031 tokens ( 38.12 ms per token, 26.23 tokens per second) 61.22.290.442 I slot print_timing: id 3 | task 9208 | eval time = 5033.62 ms / 2 tokens ( 5033.62 ms per token, 0.20 tokens per second) 61.22.290.442 I slot print_timing: id 3 | task 9208 | total time = 44334.71 ms / 1033 tokens 61.22.290.443 I slot print_timing: id 3 | task 9208 | graphs reused = 7886 61.22.290.443 I slot print_timing: id 3 | task 9208 | graph reallocs = 0 / 0 (same size) / (changed size) 61.22.290.471 I slot release: id 3 | task 9208 | stop processing: n_tokens = 1032, truncated = 0 61.22.290.481 I slot print_timing: id 1 | task 9213 | prompt processing, n_tokens = 555, progress = 0.52, t = 18.14 s / 30.60 tokens per second 61.22.299.014 I slot print_timing: id 2 | task 9214 | prompt processing, n_tokens = 590, progress = 0.53, t = 18.14 s / 32.53 tokens per second 61.28.798.061 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 61.28.798.134 I slot launch_slot_: id 0 | task 9219 | processing task, is_child = 0 61.28.798.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 61.29.559.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 61.29.559.856 I slot launch_slot_: id 3 | task 9220 | processing task, is_child = 0 61.29.567.428 I slot print_timing: id 1 | task 9213 | prompt processing, n_tokens = 878, progress = 0.82, t = 24.64 s / 35.63 tokens per second 61.29.571.834 I slot print_timing: id 2 | task 9214 | prompt processing, n_tokens = 878, progress = 0.79, t = 24.64 s / 35.63 tokens per second 61.38.071.852 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 163, progress = 1.00, t = 8.51 s / 19.15 tokens per second 61.38.835.320 I slot print_timing: id 1 | task 9213 | prompt processing, n_tokens = 1067, progress = 1.00, t = 33.92 s / 31.46 tokens per second 61.38.840.124 I slot print_timing: id 2 | task 9214 | prompt processing, n_tokens = 1102, progress = 1.00, t = 33.92 s / 32.49 tokens per second 61.38.845.008 I slot print_timing: id 3 | task 9220 | prompt processing, n_tokens = 148, progress = 1.00, t = 8.50 s / 17.42 tokens per second 61.39.430.134 I slot print_timing: id 0 | task 9219 | prompt eval time = 9657.99 ms / 167 tokens ( 57.83 ms per token, 17.29 tokens per second) 61.39.430.139 I slot print_timing: id 0 | task 9219 | eval time = 212.28 ms / 2 tokens ( 212.28 ms per token, 4.71 tokens per second) 61.39.430.139 I slot print_timing: id 0 | task 9219 | total time = 9870.27 ms / 169 tokens 61.39.430.140 I slot print_timing: id 0 | task 9219 | graphs reused = 7886 61.39.430.140 I slot print_timing: id 0 | task 9219 | graph reallocs = 0 / 0 (same size) / (changed size) 61.39.430.185 I slot release: id 0 | task 9219 | stop processing: n_tokens = 1046, truncated = 0 61.39.430.340 I slot print_timing: id 1 | task 9213 | prompt eval time = 35063.90 ms / 1071 tokens ( 32.74 ms per token, 30.54 tokens per second) 61.39.430.341 I slot print_timing: id 1 | task 9213 | eval time = 212.32 ms / 2 tokens ( 212.32 ms per token, 4.71 tokens per second) 61.39.430.342 I slot print_timing: id 1 | task 9213 | total time = 35276.23 ms / 1073 tokens 61.39.430.342 I slot print_timing: id 1 | task 9213 | graphs reused = 7886 61.39.430.342 I slot print_timing: id 1 | task 9213 | graph reallocs = 0 / 0 (same size) / (changed size) 61.39.430.374 I slot release: id 1 | task 9213 | stop processing: n_tokens = 1072, truncated = 0 61.39.430.534 I slot print_timing: id 2 | task 9214 | prompt eval time = 35064.02 ms / 1106 tokens ( 31.70 ms per token, 31.54 tokens per second) 61.39.430.536 I slot print_timing: id 2 | task 9214 | eval time = 212.32 ms / 2 tokens ( 212.32 ms per token, 4.71 tokens per second) 61.39.430.537 I slot print_timing: id 2 | task 9214 | total time = 35276.34 ms / 1108 tokens 61.39.430.537 I slot print_timing: id 2 | task 9214 | graphs reused = 7886 61.39.430.537 I slot print_timing: id 2 | task 9214 | graph reallocs = 0 / 0 (same size) / (changed size) 61.39.430.569 I slot release: id 2 | task 9214 | stop processing: n_tokens = 1107, truncated = 0 61.39.430.725 I slot print_timing: id 3 | task 9220 | prompt eval time = 9642.15 ms / 152 tokens ( 63.44 ms per token, 15.76 tokens per second) 61.39.430.727 I slot print_timing: id 3 | task 9220 | eval time = 212.30 ms / 2 tokens ( 212.30 ms per token, 4.71 tokens per second) 61.39.430.728 I slot print_timing: id 3 | task 9220 | total time = 9854.45 ms / 154 tokens 61.39.430.728 I slot print_timing: id 3 | task 9220 | graphs reused = 7886 61.39.430.728 I slot print_timing: id 3 | task 9220 | graph reallocs = 0 / 0 (same size) / (changed size) 61.39.430.750 I slot release: id 3 | task 9220 | stop processing: n_tokens = 1031, truncated = 0 61.39.440.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 82495171990 61.39.440.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.281 MiB) 61.39.460.277 I slot launch_slot_: id 0 | task 9224 | processing task, is_child = 0 61.39.460.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.218 MiB) 61.39.481.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.031 MiB) 61.39.500.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 61.39.519.333 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 82495172179 61.39.519.442 I slot launch_slot_: id 1 | task 9225 | processing task, is_child = 0 61.39.519.545 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 82495172374 61.39.519.622 I slot launch_slot_: id 2 | task 9226 | processing task, is_child = 0 61.39.519.676 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 82495172555 61.39.519.753 I slot launch_slot_: id 3 | task 9227 | processing task, is_child = 0 61.45.217.416 I slot print_timing: id 0 | task 9224 | prompt processing, n_tokens = 136, progress = 0.19, t = 5.70 s / 23.87 tokens per second 61.45.681.666 I slot print_timing: id 1 | task 9225 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.70 s / 23.87 tokens per second 61.45.686.209 I slot print_timing: id 2 | task 9226 | prompt processing, n_tokens = 136, progress = 0.17, t = 5.70 s / 23.87 tokens per second 61.45.690.898 I slot print_timing: id 3 | task 9227 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.70 s / 23.87 tokens per second 61.50.548.519 I slot print_timing: id 0 | task 9224 | prompt processing, n_tokens = 213, progress = 0.29, t = 11.03 s / 19.31 tokens per second 61.50.976.336 I slot print_timing: id 1 | task 9225 | prompt processing, n_tokens = 224, progress = 0.30, t = 11.03 s / 20.31 tokens per second 61.50.982.632 I slot print_timing: id 2 | task 9226 | prompt processing, n_tokens = 259, progress = 0.32, t = 11.03 s / 23.48 tokens per second 61.50.982.639 I slot print_timing: id 3 | task 9227 | prompt processing, n_tokens = 237, progress = 0.31, t = 11.03 s / 21.49 tokens per second 62.01.036.010 I slot print_timing: id 0 | task 9224 | prompt processing, n_tokens = 623, progress = 0.85, t = 21.52 s / 28.95 tokens per second 62.05.327.394 I slot print_timing: id 1 | task 9225 | prompt processing, n_tokens = 623, progress = 0.84, t = 21.52 s / 28.95 tokens per second 62.05.332.217 I slot print_timing: id 2 | task 9226 | prompt processing, n_tokens = 281, progress = 0.35, t = 21.52 s / 13.06 tokens per second 62.05.336.664 I slot print_timing: id 3 | task 9227 | prompt processing, n_tokens = 623, progress = 0.83, t = 21.52 s / 28.96 tokens per second 62.11.312.870 I slot print_timing: id 0 | task 9224 | prompt processing, n_tokens = 725, progress = 0.99, t = 31.79 s / 22.80 tokens per second 62.13.869.596 I slot print_timing: id 1 | task 9225 | prompt processing, n_tokens = 736, progress = 0.99, t = 31.79 s / 23.15 tokens per second 62.13.883.408 I slot print_timing: id 2 | task 9226 | prompt processing, n_tokens = 623, progress = 0.78, t = 31.79 s / 19.60 tokens per second 62.13.896.519 I slot print_timing: id 3 | task 9227 | prompt processing, n_tokens = 749, progress = 0.99, t = 31.79 s / 23.56 tokens per second 62.16.453.099 I slot print_timing: id 2 | task 9226 | prompt processing, n_tokens = 793, progress = 0.99, t = 36.93 s / 21.47 tokens per second 62.16.943.251 I slot print_timing: id 0 | task 9224 | prompt eval time = 36932.55 ms / 729 tokens ( 50.66 ms per token, 19.74 tokens per second) 62.16.943.256 I slot print_timing: id 0 | task 9224 | eval time = 490.93 ms / 2 tokens ( 490.93 ms per token, 2.04 tokens per second) 62.16.943.256 I slot print_timing: id 0 | task 9224 | total time = 37423.49 ms / 731 tokens 62.16.943.257 I slot print_timing: id 0 | task 9224 | graphs reused = 7886 62.16.943.257 I slot print_timing: id 0 | task 9224 | graph reallocs = 0 / 0 (same size) / (changed size) 62.16.943.290 I slot release: id 0 | task 9224 | stop processing: n_tokens = 730, truncated = 0 62.16.943.558 I slot print_timing: id 1 | task 9225 | prompt eval time = 36932.86 ms / 740 tokens ( 49.91 ms per token, 20.04 tokens per second) 62.16.943.566 I slot print_timing: id 1 | task 9225 | eval time = 490.86 ms / 2 tokens ( 490.86 ms per token, 2.04 tokens per second) 62.16.943.566 I slot print_timing: id 1 | task 9225 | total time = 37423.71 ms / 742 tokens 62.16.943.566 I slot print_timing: id 1 | task 9225 | graphs reused = 7886 62.16.943.567 I slot print_timing: id 1 | task 9225 | graph reallocs = 0 / 0 (same size) / (changed size) 62.16.943.593 I slot release: id 1 | task 9225 | stop processing: n_tokens = 741, truncated = 0 62.16.944.532 I slot print_timing: id 3 | task 9227 | prompt eval time = 36933.09 ms / 753 tokens ( 49.05 ms per token, 20.39 tokens per second) 62.16.944.538 I slot print_timing: id 3 | task 9227 | eval time = 491.44 ms / 2 tokens ( 491.44 ms per token, 2.03 tokens per second) 62.16.944.538 I slot print_timing: id 3 | task 9227 | total time = 37424.53 ms / 755 tokens 62.16.944.539 I slot print_timing: id 3 | task 9227 | graphs reused = 7886 62.16.944.539 I slot print_timing: id 3 | task 9227 | graph reallocs = 0 / 0 (same size) / (changed size) 62.16.944.579 I slot release: id 3 | task 9227 | stop processing: n_tokens = 754, truncated = 0 62.17.047.093 I slot print_timing: id 2 | task 9226 | prompt eval time = 37424.15 ms / 797 tokens ( 46.96 ms per token, 21.30 tokens per second) 62.17.047.097 I slot print_timing: id 2 | task 9226 | eval time = 103.02 ms / 2 tokens ( 103.02 ms per token, 9.71 tokens per second) 62.17.047.097 I slot print_timing: id 2 | task 9226 | total time = 37527.17 ms / 799 tokens 62.17.047.098 I slot print_timing: id 2 | task 9226 | graphs reused = 7886 62.17.047.098 I slot print_timing: id 2 | task 9226 | graph reallocs = 0 / 0 (same size) / (changed size) 62.17.047.128 I slot release: id 2 | task 9226 | stop processing: n_tokens = 798, truncated = 0 62.17.047.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 62.17.047.163 I slot launch_slot_: id 0 | task 9235 | processing task, is_child = 0 62.17.047.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.468 MiB) 62.17.069.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.406 MiB) 62.17.088.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.906 MiB) 62.17.114.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 62.17.114.483 I slot launch_slot_: id 1 | task 9236 | processing task, is_child = 0 62.17.114.568 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.816 62.17.114.592 I slot launch_slot_: id 2 | task 9237 | processing task, is_child = 0 62.17.114.642 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.863 62.17.114.664 I slot launch_slot_: id 3 | task 9238 | processing task, is_child = 0 62.22.993.420 I slot print_timing: id 0 | task 9235 | prompt processing, n_tokens = 106, progress = 0.99, t = 5.88 s / 18.03 tokens per second 62.23.289.633 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.87 s / 19.08 tokens per second 62.23.295.198 I slot print_timing: id 2 | task 9237 | prompt processing, n_tokens = 119, progress = 0.99, t = 5.86 s / 20.29 tokens per second 62.23.299.756 I slot print_timing: id 3 | task 9238 | prompt processing, n_tokens = 128, progress = 0.99, t = 5.86 s / 21.86 tokens per second 62.23.882.356 I slot print_timing: id 0 | task 9235 | prompt eval time = 6556.08 ms / 110 tokens ( 59.60 ms per token, 16.78 tokens per second) 62.23.882.358 I slot print_timing: id 0 | task 9235 | eval time = 211.60 ms / 2 tokens ( 211.60 ms per token, 4.73 tokens per second) 62.23.882.359 I slot print_timing: id 0 | task 9235 | total time = 6767.68 ms / 112 tokens 62.23.882.360 I slot print_timing: id 0 | task 9235 | graphs reused = 7886 62.23.882.360 I slot print_timing: id 0 | task 9235 | graph reallocs = 0 / 0 (same size) / (changed size) 62.23.882.396 I slot release: id 0 | task 9235 | stop processing: n_tokens = 734, truncated = 0 62.23.882.541 I slot print_timing: id 1 | task 9236 | prompt eval time = 6548.64 ms / 116 tokens ( 56.45 ms per token, 17.71 tokens per second) 62.23.882.543 I slot print_timing: id 1 | task 9236 | eval time = 211.63 ms / 2 tokens ( 211.63 ms per token, 4.73 tokens per second) 62.23.882.544 I slot print_timing: id 1 | task 9236 | total time = 6760.27 ms / 118 tokens 62.23.882.544 I slot print_timing: id 1 | task 9236 | graphs reused = 7886 62.23.882.544 I slot print_timing: id 1 | task 9236 | graph reallocs = 0 / 0 (same size) / (changed size) 62.23.882.566 I slot release: id 1 | task 9236 | stop processing: n_tokens = 740, truncated = 0 62.23.882.721 I slot print_timing: id 2 | task 9237 | prompt eval time = 6541.27 ms / 123 tokens ( 53.18 ms per token, 18.80 tokens per second) 62.23.882.723 I slot print_timing: id 2 | task 9237 | eval time = 211.63 ms / 2 tokens ( 211.63 ms per token, 4.73 tokens per second) 62.23.882.723 I slot print_timing: id 2 | task 9237 | total time = 6752.90 ms / 125 tokens 62.23.882.723 I slot print_timing: id 2 | task 9237 | graphs reused = 7886 62.23.882.724 I slot print_timing: id 2 | task 9237 | graph reallocs = 0 / 0 (same size) / (changed size) 62.23.882.742 I slot release: id 2 | task 9237 | stop processing: n_tokens = 747, truncated = 0 62.23.882.902 I slot print_timing: id 3 | task 9238 | prompt eval time = 6533.95 ms / 132 tokens ( 49.50 ms per token, 20.20 tokens per second) 62.23.882.903 I slot print_timing: id 3 | task 9238 | eval time = 211.58 ms / 2 tokens ( 211.58 ms per token, 4.73 tokens per second) 62.23.882.903 I slot print_timing: id 3 | task 9238 | total time = 6745.53 ms / 134 tokens 62.23.882.903 I slot print_timing: id 3 | task 9238 | graphs reused = 7886 62.23.882.904 I slot print_timing: id 3 | task 9238 | graph reallocs = 0 / 0 (same size) / (changed size) 62.23.882.928 I slot release: id 3 | task 9238 | stop processing: n_tokens = 756, truncated = 0 62.23.892.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.887 62.23.892.411 I slot launch_slot_: id 0 | task 9242 | processing task, is_child = 0 62.23.892.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.593 MiB) 62.23.911.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 62.23.930.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.655 MiB) 62.23.948.119 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 82539624372 62.23.948.225 I slot launch_slot_: id 1 | task 9243 | processing task, is_child = 0 62.23.948.307 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 747, t_last = 82539624547 62.23.948.367 I slot launch_slot_: id 2 | task 9244 | processing task, is_child = 0 62.23.948.408 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 82539624733 62.23.948.464 I slot launch_slot_: id 3 | task 9245 | processing task, is_child = 0 62.29.315.664 I slot print_timing: id 0 | task 9242 | prompt processing, n_tokens = 120, progress = 0.99, t = 5.37 s / 22.36 tokens per second 62.30.848.458 I slot print_timing: id 1 | task 9243 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.36 s / 30.23 tokens per second 62.30.852.873 I slot print_timing: id 2 | task 9244 | prompt processing, n_tokens = 162, progress = 0.16, t = 5.36 s / 30.23 tokens per second 62.30.857.302 I slot print_timing: id 3 | task 9245 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.36 s / 30.23 tokens per second 62.37.792.707 I slot print_timing: id 1 | task 9243 | prompt processing, n_tokens = 350, progress = 0.37, t = 13.84 s / 25.30 tokens per second 62.37.792.719 I slot print_timing: id 2 | task 9244 | prompt processing, n_tokens = 350, progress = 0.35, t = 13.84 s / 25.30 tokens per second 62.37.792.726 I slot print_timing: id 3 | task 9245 | prompt processing, n_tokens = 350, progress = 0.36, t = 13.84 s / 25.30 tokens per second 62.42.443.493 I slot print_timing: id 0 | task 9242 | prompt eval time = 13844.22 ms / 124 tokens ( 111.65 ms per token, 8.96 tokens per second) 62.42.443.497 I slot print_timing: id 0 | task 9242 | eval time = 4650.80 ms / 2 tokens ( 4650.80 ms per token, 0.22 tokens per second) 62.42.443.497 I slot print_timing: id 0 | task 9242 | total time = 18495.01 ms / 126 tokens 62.42.443.498 I slot print_timing: id 0 | task 9242 | graphs reused = 7886 62.42.443.498 I slot print_timing: id 0 | task 9242 | graph reallocs = 0 / 0 (same size) / (changed size) 62.42.443.538 I slot release: id 0 | task 9242 | stop processing: n_tokens = 748, truncated = 0 62.42.443.550 I slot print_timing: id 1 | task 9243 | prompt processing, n_tokens = 439, progress = 0.46, t = 18.49 s / 23.75 tokens per second 62.42.448.653 I slot print_timing: id 2 | task 9244 | prompt processing, n_tokens = 474, progress = 0.48, t = 18.49 s / 25.64 tokens per second 62.42.453.659 I slot print_timing: id 3 | task 9245 | prompt processing, n_tokens = 457, progress = 0.47, t = 18.49 s / 24.72 tokens per second 62.55.303.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 82558185343 62.55.303.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.530 MiB) 62.55.734.398 I slot launch_slot_: id 0 | task 9250 | processing task, is_child = 0 62.55.734.480 I slot print_timing: id 1 | task 9243 | prompt processing, n_tokens = 820, progress = 0.86, t = 31.35 s / 26.16 tokens per second 62.55.738.899 I slot print_timing: id 2 | task 9244 | prompt processing, n_tokens = 820, progress = 0.83, t = 31.35 s / 26.16 tokens per second 62.55.743.325 I slot print_timing: id 3 | task 9245 | prompt processing, n_tokens = 820, progress = 0.84, t = 31.35 s / 26.16 tokens per second 63.03.022.932 I slot print_timing: id 0 | task 9250 | prompt processing, n_tokens = 162, progress = 0.16, t = 7.29 s / 22.23 tokens per second 63.03.455.886 I slot print_timing: id 1 | task 9243 | prompt processing, n_tokens = 951, progress = 1.00, t = 39.07 s / 24.34 tokens per second 63.03.463.130 I slot print_timing: id 2 | task 9244 | prompt processing, n_tokens = 986, progress = 1.00, t = 39.07 s / 25.24 tokens per second 63.03.467.829 I slot print_timing: id 3 | task 9245 | prompt processing, n_tokens = 969, progress = 1.00, t = 39.07 s / 24.80 tokens per second 63.06.021.109 I slot print_timing: id 0 | task 9250 | prompt processing, n_tokens = 350, progress = 0.34, t = 10.29 s / 34.03 tokens per second 63.08.401.169 I slot print_timing: id 1 | task 9243 | prompt eval time = 42064.37 ms / 955 tokens ( 44.05 ms per token, 22.70 tokens per second) 63.08.401.171 I slot print_timing: id 1 | task 9243 | eval time = 2380.63 ms / 2 tokens ( 2380.63 ms per token, 0.42 tokens per second) 63.08.401.172 I slot print_timing: id 1 | task 9243 | total time = 44445.00 ms / 957 tokens 63.08.401.172 I slot print_timing: id 1 | task 9243 | graphs reused = 7886 63.08.401.173 I slot print_timing: id 1 | task 9243 | graph reallocs = 0 / 0 (same size) / (changed size) 63.08.401.214 I slot release: id 1 | task 9243 | stop processing: n_tokens = 956, truncated = 0 63.08.401.450 I slot print_timing: id 2 | task 9244 | prompt eval time = 42064.60 ms / 990 tokens ( 42.49 ms per token, 23.54 tokens per second) 63.08.401.456 I slot print_timing: id 2 | task 9244 | eval time = 2380.62 ms / 2 tokens ( 2380.62 ms per token, 0.42 tokens per second) 63.08.401.456 I slot print_timing: id 2 | task 9244 | total time = 44445.21 ms / 992 tokens 63.08.401.456 I slot print_timing: id 2 | task 9244 | graphs reused = 7886 63.08.401.457 I slot print_timing: id 2 | task 9244 | graph reallocs = 0 / 0 (same size) / (changed size) 63.08.401.491 I slot release: id 2 | task 9244 | stop processing: n_tokens = 991, truncated = 0 63.08.401.734 I slot print_timing: id 3 | task 9245 | prompt eval time = 42064.81 ms / 973 tokens ( 43.23 ms per token, 23.13 tokens per second) 63.08.401.737 I slot print_timing: id 3 | task 9245 | eval time = 2380.64 ms / 2 tokens ( 2380.64 ms per token, 0.42 tokens per second) 63.08.401.738 I slot print_timing: id 3 | task 9245 | total time = 44445.44 ms / 975 tokens 63.08.401.738 I slot print_timing: id 3 | task 9245 | graphs reused = 7886 63.08.401.738 I slot print_timing: id 3 | task 9245 | graph reallocs = 0 / 0 (same size) / (changed size) 63.08.401.763 I slot release: id 3 | task 9245 | stop processing: n_tokens = 974, truncated = 0 63.08.401.771 I slot print_timing: id 0 | task 9250 | prompt processing, n_tokens = 528, progress = 0.51, t = 12.67 s / 41.68 tokens per second 63.08.414.284 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 82584143019 63.08.414.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 63.12.017.043 I slot launch_slot_: id 1 | task 9255 | processing task, is_child = 0 63.12.017.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 817.344 MiB) 63.12.036.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.592 MiB) 63.12.055.189 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 82584143296 63.12.055.295 I slot launch_slot_: id 2 | task 9256 | processing task, is_child = 0 63.12.055.344 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 82584143568 63.12.055.409 I slot launch_slot_: id 3 | task 9257 | processing task, is_child = 0 63.12.055.416 I slot print_timing: id 0 | task 9250 | prompt processing, n_tokens = 820, progress = 0.79, t = 12.68 s / 64.67 tokens per second 63.21.717.244 I slot print_timing: id 0 | task 9250 | prompt processing, n_tokens = 1040, progress = 1.00, t = 25.98 s / 40.03 tokens per second 63.23.890.720 I slot print_timing: id 1 | task 9255 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.66 s / 21.12 tokens per second 63.23.895.272 I slot print_timing: id 2 | task 9256 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.66 s / 21.12 tokens per second 63.23.899.638 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 372, progress = 0.18, t = 9.66 s / 38.52 tokens per second 63.30.793.168 I slot print_timing: id 1 | task 9255 | prompt processing, n_tokens = 350, progress = 0.31, t = 18.73 s / 18.68 tokens per second 63.30.793.185 I slot print_timing: id 2 | task 9256 | prompt processing, n_tokens = 350, progress = 0.30, t = 18.73 s / 18.68 tokens per second 63.30.793.195 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 640, progress = 0.31, t = 18.73 s / 34.16 tokens per second 63.48.451.526 I slot print_timing: id 0 | task 9250 | prompt eval time = 35058.74 ms / 1044 tokens ( 33.58 ms per token, 29.78 tokens per second) 63.48.451.529 I slot print_timing: id 0 | task 9250 | eval time = 17658.37 ms / 2 tokens (17658.37 ms per token, 0.06 tokens per second) 63.48.451.529 I slot print_timing: id 0 | task 9250 | total time = 52717.11 ms / 1046 tokens 63.48.451.530 I slot print_timing: id 0 | task 9250 | graphs reused = 7886 63.48.451.530 I slot print_timing: id 0 | task 9250 | graph reallocs = 0 / 0 (same size) / (changed size) 63.48.451.574 I slot release: id 0 | task 9250 | stop processing: n_tokens = 1045, truncated = 0 63.48.451.589 I slot print_timing: id 1 | task 9255 | prompt processing, n_tokens = 608, progress = 0.54, t = 36.39 s / 16.71 tokens per second 63.48.457.536 I slot print_timing: id 2 | task 9256 | prompt processing, n_tokens = 645, progress = 0.56, t = 36.39 s / 17.72 tokens per second 63.48.462.348 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 1575, progress = 0.75, t = 36.39 s / 43.28 tokens per second 63.58.730.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 82624193379 63.58.730.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.460 MiB) 63.59.494.427 I slot launch_slot_: id 0 | task 9262 | processing task, is_child = 0 63.59.494.530 I slot print_timing: id 1 | task 9255 | prompt processing, n_tokens = 977, progress = 0.87, t = 46.67 s / 20.93 tokens per second 63.59.499.018 I slot print_timing: id 2 | task 9256 | prompt processing, n_tokens = 977, progress = 0.84, t = 46.67 s / 20.93 tokens per second 63.59.503.483 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 1761, progress = 0.84, t = 46.67 s / 37.73 tokens per second 64.10.116.066 I slot print_timing: id 0 | task 9262 | prompt processing, n_tokens = 372, progress = 0.18, t = 10.62 s / 35.02 tokens per second 64.11.980.899 I slot print_timing: id 1 | task 9255 | prompt processing, n_tokens = 1120, progress = 1.00, t = 58.06 s / 19.29 tokens per second 64.11.985.454 I slot print_timing: id 2 | task 9256 | prompt processing, n_tokens = 1157, progress = 1.00, t = 58.06 s / 19.93 tokens per second 64.11.989.954 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 2087, progress = 1.00, t = 58.06 s / 35.95 tokens per second 64.15.663.494 I slot print_timing: id 0 | task 9262 | prompt processing, n_tokens = 640, progress = 0.31, t = 16.17 s / 39.58 tokens per second 64.26.639.306 I slot print_timing: id 1 | task 9255 | prompt eval time = 63603.22 ms / 1124 tokens ( 56.59 ms per token, 17.67 tokens per second) 64.26.639.308 I slot print_timing: id 1 | task 9255 | eval time = 10976.24 ms / 2 tokens (10976.24 ms per token, 0.09 tokens per second) 64.26.639.309 I slot print_timing: id 1 | task 9255 | total time = 74579.46 ms / 1126 tokens 64.26.639.309 I slot print_timing: id 1 | task 9255 | graphs reused = 7886 64.26.639.310 I slot print_timing: id 1 | task 9255 | graph reallocs = 0 / 0 (same size) / (changed size) 64.26.639.359 I slot release: id 1 | task 9255 | stop processing: n_tokens = 1125, truncated = 0 64.26.639.529 I slot print_timing: id 2 | task 9256 | prompt eval time = 63603.36 ms / 1161 tokens ( 54.78 ms per token, 18.25 tokens per second) 64.26.639.532 I slot print_timing: id 2 | task 9256 | eval time = 10976.25 ms / 2 tokens (10976.25 ms per token, 0.09 tokens per second) 64.26.639.532 I slot print_timing: id 2 | task 9256 | total time = 74579.61 ms / 1163 tokens 64.26.639.532 I slot print_timing: id 2 | task 9256 | graphs reused = 7886 64.26.639.533 I slot print_timing: id 2 | task 9256 | graph reallocs = 0 / 0 (same size) / (changed size) 64.26.639.561 I slot release: id 2 | task 9256 | stop processing: n_tokens = 1162, truncated = 0 64.26.639.816 I slot print_timing: id 3 | task 9257 | prompt eval time = 63603.51 ms / 2091 tokens ( 30.42 ms per token, 32.88 tokens per second) 64.26.639.820 I slot print_timing: id 3 | task 9257 | eval time = 10976.33 ms / 2 tokens (10976.33 ms per token, 0.09 tokens per second) 64.26.639.820 I slot print_timing: id 3 | task 9257 | total time = 74579.84 ms / 2093 tokens 64.26.639.820 I slot print_timing: id 3 | task 9257 | graphs reused = 7886 64.26.639.820 I slot print_timing: id 3 | task 9257 | graph reallocs = 0 / 0 (same size) / (changed size) 64.26.639.891 I slot release: id 3 | task 9257 | stop processing: n_tokens = 2092, truncated = 0 64.26.639.901 I slot print_timing: id 0 | task 9262 | prompt processing, n_tokens = 1578, progress = 0.75, t = 27.14 s / 58.13 tokens per second 64.26.650.812 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.856 64.26.650.841 I slot launch_slot_: id 3 | task 9267 | processing task, is_child = 0 64.26.650.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.024 MiB) 64.28.870.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.273 MiB) 64.28.889.125 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 82662381164 64.28.889.251 I slot launch_slot_: id 1 | task 9268 | processing task, is_child = 0 64.28.889.307 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 82662381366 64.28.889.383 I slot launch_slot_: id 2 | task 9269 | processing task, is_child = 0 64.28.889.390 I slot print_timing: id 0 | task 9262 | prompt processing, n_tokens = 1761, progress = 0.84, t = 27.16 s / 64.85 tokens per second 64.43.454.520 I slot print_timing: id 0 | task 9262 | prompt processing, n_tokens = 2090, progress = 1.00, t = 43.96 s / 47.54 tokens per second 64.44.621.830 I slot print_timing: id 1 | task 9268 | prompt processing, n_tokens = 372, progress = 0.18, t = 14.56 s / 25.55 tokens per second 64.44.626.461 I slot print_timing: id 2 | task 9269 | prompt processing, n_tokens = 372, progress = 0.18, t = 14.56 s / 25.55 tokens per second 64.44.631.051 I slot print_timing: id 3 | task 9267 | prompt processing, n_tokens = 276, progress = 1.00, t = 14.56 s / 18.96 tokens per second 64.51.018.772 I slot print_timing: id 1 | task 9268 | prompt processing, n_tokens = 640, progress = 0.31, t = 22.12 s / 28.93 tokens per second 64.51.018.796 I slot print_timing: id 2 | task 9269 | prompt processing, n_tokens = 640, progress = 0.30, t = 22.12 s / 28.93 tokens per second 65.12.582.262 I slot print_timing: id 0 | task 9262 | prompt eval time = 51524.14 ms / 2094 tokens ( 24.61 ms per token, 40.64 tokens per second) 65.12.582.267 I slot print_timing: id 0 | task 9262 | eval time = 21563.67 ms / 2 tokens (21563.67 ms per token, 0.05 tokens per second) 65.12.582.268 I slot print_timing: id 0 | task 9262 | total time = 73087.81 ms / 2096 tokens 65.12.582.268 I slot print_timing: id 0 | task 9262 | graphs reused = 7886 65.12.582.269 I slot print_timing: id 0 | task 9262 | graph reallocs = 0 / 0 (same size) / (changed size) 65.12.582.353 I slot release: id 0 | task 9262 | stop processing: n_tokens = 2095, truncated = 0 65.12.582.522 I slot print_timing: id 3 | task 9267 | prompt eval time = 22124.72 ms / 280 tokens ( 79.02 ms per token, 12.66 tokens per second) 65.12.582.529 I slot print_timing: id 3 | task 9267 | eval time = 21563.76 ms / 2 tokens (21563.76 ms per token, 0.05 tokens per second) 65.12.582.530 I slot print_timing: id 3 | task 9267 | total time = 43688.48 ms / 282 tokens 65.12.582.530 I slot print_timing: id 3 | task 9267 | graphs reused = 7886 65.12.582.530 I slot print_timing: id 3 | task 9267 | graph reallocs = 0 / 0 (same size) / (changed size) 65.12.582.589 I slot release: id 3 | task 9267 | stop processing: n_tokens = 2042, truncated = 0 65.12.582.601 I slot print_timing: id 1 | task 9268 | prompt processing, n_tokens = 1541, progress = 0.75, t = 43.69 s / 35.27 tokens per second 65.12.588.882 I slot print_timing: id 2 | task 9269 | prompt processing, n_tokens = 1589, progress = 0.75, t = 43.69 s / 36.37 tokens per second 65.16.657.082 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.854 65.16.657.148 I slot launch_slot_: id 0 | task 9274 | processing task, is_child = 0 65.16.657.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 65.17.439.221 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.877 65.17.439.299 I slot launch_slot_: id 3 | task 9275 | processing task, is_child = 0 65.17.446.884 I slot print_timing: id 1 | task 9268 | prompt processing, n_tokens = 1761, progress = 0.86, t = 47.76 s / 36.87 tokens per second 65.17.451.379 I slot print_timing: id 2 | task 9269 | prompt processing, n_tokens = 1761, progress = 0.84, t = 47.76 s / 36.87 tokens per second 65.32.361.727 I slot print_timing: id 0 | task 9274 | prompt processing, n_tokens = 296, progress = 1.00, t = 14.92 s / 19.84 tokens per second 65.32.803.738 I slot print_timing: id 1 | task 9268 | prompt processing, n_tokens = 2053, progress = 1.00, t = 63.47 s / 32.35 tokens per second 65.32.808.355 I slot print_timing: id 2 | task 9269 | prompt processing, n_tokens = 2101, progress = 1.00, t = 63.47 s / 33.10 tokens per second 65.32.812.964 I slot print_timing: id 3 | task 9275 | prompt processing, n_tokens = 365, progress = 1.00, t = 14.91 s / 24.49 tokens per second 65.33.407.260 I slot print_timing: id 0 | task 9274 | prompt eval time = 15753.62 ms / 300 tokens ( 52.51 ms per token, 19.04 tokens per second) 65.33.407.265 I slot print_timing: id 0 | task 9274 | eval time = 214.33 ms / 2 tokens ( 214.33 ms per token, 4.67 tokens per second) 65.33.407.265 I slot print_timing: id 0 | task 9274 | total time = 15967.95 ms / 302 tokens 65.33.407.266 I slot print_timing: id 0 | task 9274 | graphs reused = 7887 65.33.407.266 I slot print_timing: id 0 | task 9274 | graph reallocs = 0 / 0 (same size) / (changed size) 65.33.407.341 I slot release: id 0 | task 9274 | stop processing: n_tokens = 2062, truncated = 0 65.33.407.497 I slot print_timing: id 1 | task 9268 | prompt eval time = 64299.21 ms / 2057 tokens ( 31.26 ms per token, 31.99 tokens per second) 65.33.407.499 I slot print_timing: id 1 | task 9268 | eval time = 214.42 ms / 2 tokens ( 214.42 ms per token, 4.66 tokens per second) 65.33.407.500 I slot print_timing: id 1 | task 9268 | total time = 64513.63 ms / 2059 tokens 65.33.407.500 I slot print_timing: id 1 | task 9268 | graphs reused = 7887 65.33.407.500 I slot print_timing: id 1 | task 9268 | graph reallocs = 0 / 0 (same size) / (changed size) 65.33.407.553 I slot release: id 1 | task 9268 | stop processing: n_tokens = 2058, truncated = 0 65.33.407.720 I slot print_timing: id 2 | task 9269 | prompt eval time = 64299.28 ms / 2105 tokens ( 30.55 ms per token, 32.74 tokens per second) 65.33.407.722 I slot print_timing: id 2 | task 9269 | eval time = 214.48 ms / 2 tokens ( 214.48 ms per token, 4.66 tokens per second) 65.33.407.723 I slot print_timing: id 2 | task 9269 | total time = 64513.76 ms / 2107 tokens 65.33.407.724 I slot print_timing: id 2 | task 9269 | graphs reused = 7887 65.33.407.724 I slot print_timing: id 2 | task 9269 | graph reallocs = 0 / 0 (same size) / (changed size) 65.33.407.770 I slot release: id 2 | task 9269 | stop processing: n_tokens = 2106, truncated = 0 65.33.407.961 I slot print_timing: id 3 | task 9275 | prompt eval time = 15737.43 ms / 369 tokens ( 42.65 ms per token, 23.45 tokens per second) 65.33.407.963 I slot print_timing: id 3 | task 9275 | eval time = 214.43 ms / 2 tokens ( 214.43 ms per token, 4.66 tokens per second) 65.33.407.964 I slot print_timing: id 3 | task 9275 | total time = 15951.86 ms / 371 tokens 65.33.407.964 I slot print_timing: id 3 | task 9275 | graphs reused = 7887 65.33.407.964 I slot print_timing: id 3 | task 9275 | graph reallocs = 0 / 0 (same size) / (changed size) 65.33.408.009 I slot release: id 3 | task 9275 | stop processing: n_tokens = 2131, truncated = 0 65.33.418.914 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 65.33.418.943 I slot launch_slot_: id 1 | task 9279 | processing task, is_child = 0 65.33.419.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.836 MiB) 65.33.419.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.398 MiB) 65.33.456.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.898 MiB) 65.33.495.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.903 MiB) 65.33.544.163 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.850 65.33.544.229 I slot launch_slot_: id 2 | task 9280 | processing task, is_child = 0 65.33.544.420 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.840 65.33.544.445 I slot launch_slot_: id 3 | task 9281 | processing task, is_child = 0 65.33.544.530 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.868 65.33.544.551 I slot launch_slot_: id 0 | task 9282 | processing task, is_child = 0 65.47.578.428 I slot print_timing: id 0 | task 9282 | prompt processing, n_tokens = 463, progress = 1.00, t = 14.03 s / 32.99 tokens per second 65.49.092.982 I slot print_timing: id 1 | task 9279 | prompt processing, n_tokens = 206, progress = 1.00, t = 14.03 s / 14.69 tokens per second 65.49.097.601 I slot print_timing: id 2 | task 9280 | prompt processing, n_tokens = 376, progress = 1.00, t = 14.02 s / 26.82 tokens per second 65.49.102.213 I slot print_timing: id 3 | task 9281 | prompt processing, n_tokens = 254, progress = 1.00, t = 14.01 s / 18.13 tokens per second 65.49.696.374 I slot print_timing: id 0 | task 9282 | prompt eval time = 15937.39 ms / 467 tokens ( 34.13 ms per token, 29.30 tokens per second) 65.49.696.379 I slot print_timing: id 0 | task 9282 | eval time = 214.42 ms / 2 tokens ( 214.42 ms per token, 4.66 tokens per second) 65.49.696.380 I slot print_timing: id 0 | task 9282 | total time = 16151.81 ms / 469 tokens 65.49.696.380 I slot print_timing: id 0 | task 9282 | graphs reused = 7887 65.49.696.380 I slot print_timing: id 0 | task 9282 | graph reallocs = 0 / 0 (same size) / (changed size) 65.49.696.460 I slot release: id 0 | task 9282 | stop processing: n_tokens = 2229, truncated = 0 65.49.696.607 I slot print_timing: id 1 | task 9279 | prompt eval time = 15929.74 ms / 210 tokens ( 75.86 ms per token, 13.18 tokens per second) 65.49.696.609 I slot print_timing: id 1 | task 9279 | eval time = 214.50 ms / 2 tokens ( 214.50 ms per token, 4.66 tokens per second) 65.49.696.610 I slot print_timing: id 1 | task 9279 | total time = 16144.23 ms / 212 tokens 65.49.696.611 I slot print_timing: id 1 | task 9279 | graphs reused = 7887 65.49.696.611 I slot print_timing: id 1 | task 9279 | graph reallocs = 0 / 0 (same size) / (changed size) 65.49.696.666 I slot release: id 1 | task 9279 | stop processing: n_tokens = 1972, truncated = 0 65.49.696.824 I slot print_timing: id 2 | task 9280 | prompt eval time = 15922.22 ms / 380 tokens ( 41.90 ms per token, 23.87 tokens per second) 65.49.696.826 I slot print_timing: id 2 | task 9280 | eval time = 214.54 ms / 2 tokens ( 214.54 ms per token, 4.66 tokens per second) 65.49.696.827 I slot print_timing: id 2 | task 9280 | total time = 16136.76 ms / 382 tokens 65.49.696.827 I slot print_timing: id 2 | task 9280 | graphs reused = 7887 65.49.696.827 I slot print_timing: id 2 | task 9280 | graph reallocs = 0 / 0 (same size) / (changed size) 65.49.696.875 I slot release: id 2 | task 9280 | stop processing: n_tokens = 2142, truncated = 0 65.49.697.039 I slot print_timing: id 3 | task 9281 | prompt eval time = 15914.79 ms / 258 tokens ( 61.69 ms per token, 16.21 tokens per second) 65.49.697.042 I slot print_timing: id 3 | task 9281 | eval time = 214.53 ms / 2 tokens ( 214.53 ms per token, 4.66 tokens per second) 65.49.697.042 I slot print_timing: id 3 | task 9281 | total time = 16129.31 ms / 260 tokens 65.49.697.043 I slot print_timing: id 3 | task 9281 | graphs reused = 7887 65.49.697.043 I slot print_timing: id 3 | task 9281 | graph reallocs = 0 / 0 (same size) / (changed size) 65.49.697.082 I slot release: id 3 | task 9281 | stop processing: n_tokens = 2020, truncated = 0 65.49.708.881 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.803 65.49.708.911 I slot launch_slot_: id 0 | task 9286 | processing task, is_child = 0 65.49.709.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.091 MiB) 65.49.733.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.028 MiB) 65.49.787.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.467 MiB) 65.49.839.537 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.907 65.49.839.606 I slot launch_slot_: id 1 | task 9287 | processing task, is_child = 0 65.49.839.789 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.836 65.49.839.811 I slot launch_slot_: id 2 | task 9288 | processing task, is_child = 0 65.49.839.902 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.886 65.49.839.925 I slot launch_slot_: id 3 | task 9289 | processing task, is_child = 0 66.02.376.379 I slot print_timing: id 0 | task 9286 | prompt processing, n_tokens = 249, progress = 1.00, t = 12.54 s / 19.86 tokens per second 66.03.154.340 I slot print_timing: id 1 | task 9287 | prompt processing, n_tokens = 208, progress = 1.00, t = 12.53 s / 16.60 tokens per second 66.03.158.967 I slot print_timing: id 2 | task 9288 | prompt processing, n_tokens = 300, progress = 1.00, t = 12.52 s / 23.96 tokens per second 66.03.163.550 I slot print_timing: id 3 | task 9289 | prompt processing, n_tokens = 341, progress = 1.00, t = 12.51 s / 27.25 tokens per second 66.03.757.395 I slot print_timing: id 0 | task 9286 | prompt eval time = 13703.22 ms / 253 tokens ( 54.16 ms per token, 18.46 tokens per second) 66.03.757.397 I slot print_timing: id 0 | task 9286 | eval time = 214.24 ms / 2 tokens ( 214.24 ms per token, 4.67 tokens per second) 66.03.757.398 I slot print_timing: id 0 | task 9286 | total time = 13917.46 ms / 255 tokens 66.03.757.398 I slot print_timing: id 0 | task 9286 | graphs reused = 7887 66.03.757.399 I slot print_timing: id 0 | task 9286 | graph reallocs = 0 / 0 (same size) / (changed size) 66.03.757.469 I slot release: id 0 | task 9286 | stop processing: n_tokens = 2015, truncated = 0 66.03.757.628 I slot print_timing: id 1 | task 9287 | prompt eval time = 13695.81 ms / 212 tokens ( 64.60 ms per token, 15.48 tokens per second) 66.03.757.632 I slot print_timing: id 1 | task 9287 | eval time = 214.28 ms / 2 tokens ( 214.28 ms per token, 4.67 tokens per second) 66.03.757.633 I slot print_timing: id 1 | task 9287 | total time = 13910.09 ms / 214 tokens 66.03.757.633 I slot print_timing: id 1 | task 9287 | graphs reused = 7887 66.03.757.633 I slot print_timing: id 1 | task 9287 | graph reallocs = 0 / 0 (same size) / (changed size) 66.03.757.694 I slot release: id 1 | task 9287 | stop processing: n_tokens = 1974, truncated = 0 66.03.757.883 I slot print_timing: id 2 | task 9288 | prompt eval time = 13688.42 ms / 304 tokens ( 45.03 ms per token, 22.21 tokens per second) 66.03.757.885 I slot print_timing: id 2 | task 9288 | eval time = 214.34 ms / 2 tokens ( 214.34 ms per token, 4.67 tokens per second) 66.03.757.885 I slot print_timing: id 2 | task 9288 | total time = 13902.76 ms / 306 tokens 66.03.757.886 I slot print_timing: id 2 | task 9288 | graphs reused = 7887 66.03.757.886 I slot print_timing: id 2 | task 9288 | graph reallocs = 0 / 0 (same size) / (changed size) 66.03.757.931 I slot release: id 2 | task 9288 | stop processing: n_tokens = 2066, truncated = 0 66.03.758.107 I slot print_timing: id 3 | task 9289 | prompt eval time = 13681.06 ms / 345 tokens ( 39.66 ms per token, 25.22 tokens per second) 66.03.758.109 I slot print_timing: id 3 | task 9289 | eval time = 214.34 ms / 2 tokens ( 214.34 ms per token, 4.67 tokens per second) 66.03.758.109 I slot print_timing: id 3 | task 9289 | total time = 13895.41 ms / 347 tokens 66.03.758.110 I slot print_timing: id 3 | task 9289 | graphs reused = 7887 66.03.758.110 I slot print_timing: id 3 | task 9289 | graph reallocs = 0 / 0 (same size) / (changed size) 66.03.758.154 I slot release: id 3 | task 9289 | stop processing: n_tokens = 2107, truncated = 0 66.03.767.974 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.888 66.03.768.000 I slot launch_slot_: id 0 | task 9293 | processing task, is_child = 0 66.03.768.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 818.469 MiB) 66.03.817.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 820.783 MiB) 66.03.870.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.803 MiB) 66.03.919.385 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 66.03.919.458 I slot launch_slot_: id 2 | task 9294 | processing task, is_child = 0 66.03.919.636 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 66.03.919.659 I slot launch_slot_: id 3 | task 9295 | processing task, is_child = 0 66.03.919.740 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.906 66.03.919.763 I slot launch_slot_: id 1 | task 9296 | processing task, is_child = 0 66.18.298.235 I slot print_timing: id 0 | task 9293 | prompt processing, n_tokens = 401, progress = 1.00, t = 14.38 s / 27.89 tokens per second 66.19.083.250 I slot print_timing: id 1 | task 9296 | prompt processing, n_tokens = 300, progress = 1.00, t = 14.37 s / 20.88 tokens per second 66.19.088.252 I slot print_timing: id 2 | task 9294 | prompt processing, n_tokens = 349, progress = 1.00, t = 14.36 s / 24.30 tokens per second 66.19.093.357 I slot print_timing: id 3 | task 9295 | prompt processing, n_tokens = 206, progress = 1.00, t = 14.36 s / 14.35 tokens per second 66.19.687.777 I slot print_timing: id 0 | task 9293 | prompt eval time = 15553.86 ms / 405 tokens ( 38.40 ms per token, 26.04 tokens per second) 66.19.687.779 I slot print_timing: id 0 | task 9293 | eval time = 214.14 ms / 2 tokens ( 214.14 ms per token, 4.67 tokens per second) 66.19.687.780 I slot print_timing: id 0 | task 9293 | total time = 15768.00 ms / 407 tokens 66.19.687.780 I slot print_timing: id 0 | task 9293 | graphs reused = 7887 66.19.687.781 I slot print_timing: id 0 | task 9293 | graph reallocs = 0 / 0 (same size) / (changed size) 66.19.687.859 I slot release: id 0 | task 9293 | stop processing: n_tokens = 2167, truncated = 0 66.19.688.018 I slot print_timing: id 1 | task 9296 | prompt eval time = 15546.48 ms / 304 tokens ( 51.14 ms per token, 19.55 tokens per second) 66.19.688.020 I slot print_timing: id 1 | task 9296 | eval time = 214.18 ms / 2 tokens ( 214.18 ms per token, 4.67 tokens per second) 66.19.688.021 I slot print_timing: id 1 | task 9296 | total time = 15760.66 ms / 306 tokens 66.19.688.021 I slot print_timing: id 1 | task 9296 | graphs reused = 7887 66.19.688.022 I slot print_timing: id 1 | task 9296 | graph reallocs = 0 / 0 (same size) / (changed size) 66.19.688.073 I slot release: id 1 | task 9296 | stop processing: n_tokens = 2066, truncated = 0 66.19.688.241 I slot print_timing: id 2 | task 9294 | prompt eval time = 15539.10 ms / 353 tokens ( 44.02 ms per token, 22.72 tokens per second) 66.19.688.245 I slot print_timing: id 2 | task 9294 | eval time = 214.20 ms / 2 tokens ( 214.20 ms per token, 4.67 tokens per second) 66.19.688.246 I slot print_timing: id 2 | task 9294 | total time = 15753.30 ms / 355 tokens 66.19.688.246 I slot print_timing: id 2 | task 9294 | graphs reused = 7887 66.19.688.246 I slot print_timing: id 2 | task 9294 | graph reallocs = 0 / 0 (same size) / (changed size) 66.19.688.292 I slot release: id 2 | task 9294 | stop processing: n_tokens = 2115, truncated = 0 66.19.688.461 I slot print_timing: id 3 | task 9295 | prompt eval time = 15531.73 ms / 210 tokens ( 73.96 ms per token, 13.52 tokens per second) 66.19.688.463 I slot print_timing: id 3 | task 9295 | eval time = 214.21 ms / 2 tokens ( 214.21 ms per token, 4.67 tokens per second) 66.19.688.464 I slot print_timing: id 3 | task 9295 | total time = 15745.93 ms / 212 tokens 66.19.688.464 I slot print_timing: id 3 | task 9295 | graphs reused = 7887 66.19.688.464 I slot print_timing: id 3 | task 9295 | graph reallocs = 0 / 0 (same size) / (changed size) 66.19.688.503 I slot release: id 3 | task 9295 | stop processing: n_tokens = 1972, truncated = 0 66.19.699.648 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 66.19.699.677 I slot launch_slot_: id 2 | task 9300 | processing task, is_child = 0 66.19.699.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.053 MiB) 66.19.754.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.804 MiB) 66.19.781.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 881.367 MiB) 66.19.805.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.826 66.19.805.853 I slot launch_slot_: id 0 | task 9301 | processing task, is_child = 0 66.19.806.036 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.866 66.19.806.060 I slot launch_slot_: id 1 | task 9302 | processing task, is_child = 0 66.19.806.151 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.908 66.19.806.172 I slot launch_slot_: id 3 | task 9303 | processing task, is_child = 0 66.31.789.773 I slot print_timing: id 0 | task 9301 | prompt processing, n_tokens = 232, progress = 1.00, t = 11.98 s / 19.36 tokens per second 66.33.656.219 I slot print_timing: id 1 | task 9302 | prompt processing, n_tokens = 268, progress = 1.00, t = 11.98 s / 22.38 tokens per second 66.33.660.800 I slot print_timing: id 2 | task 9300 | prompt processing, n_tokens = 260, progress = 1.00, t = 11.97 s / 21.72 tokens per second 66.33.665.473 I slot print_timing: id 3 | task 9303 | prompt processing, n_tokens = 409, progress = 1.00, t = 11.96 s / 34.20 tokens per second 66.34.259.564 I slot print_timing: id 0 | task 9301 | prompt eval time = 14238.99 ms / 236 tokens ( 60.33 ms per token, 16.57 tokens per second) 66.34.259.567 I slot print_timing: id 0 | task 9301 | eval time = 214.39 ms / 2 tokens ( 214.39 ms per token, 4.66 tokens per second) 66.34.259.567 I slot print_timing: id 0 | task 9301 | total time = 14453.38 ms / 238 tokens 66.34.259.568 I slot print_timing: id 0 | task 9301 | graphs reused = 7887 66.34.259.568 I slot print_timing: id 0 | task 9301 | graph reallocs = 0 / 0 (same size) / (changed size) 66.34.259.644 I slot release: id 0 | task 9301 | stop processing: n_tokens = 1998, truncated = 0 66.34.259.795 I slot print_timing: id 1 | task 9302 | prompt eval time = 14231.58 ms / 272 tokens ( 52.32 ms per token, 19.11 tokens per second) 66.34.259.797 I slot print_timing: id 1 | task 9302 | eval time = 214.42 ms / 2 tokens ( 214.42 ms per token, 4.66 tokens per second) 66.34.259.797 I slot print_timing: id 1 | task 9302 | total time = 14446.00 ms / 274 tokens 66.34.259.798 I slot print_timing: id 1 | task 9302 | graphs reused = 7887 66.34.259.798 I slot print_timing: id 1 | task 9302 | graph reallocs = 0 / 0 (same size) / (changed size) 66.34.259.846 I slot release: id 1 | task 9302 | stop processing: n_tokens = 2034, truncated = 0 66.34.260.010 I slot print_timing: id 2 | task 9300 | prompt eval time = 14224.22 ms / 264 tokens ( 53.88 ms per token, 18.56 tokens per second) 66.34.260.012 I slot print_timing: id 2 | task 9300 | eval time = 214.43 ms / 2 tokens ( 214.43 ms per token, 4.66 tokens per second) 66.34.260.012 I slot print_timing: id 2 | task 9300 | total time = 14438.65 ms / 266 tokens 66.34.260.012 I slot print_timing: id 2 | task 9300 | graphs reused = 7887 66.34.260.013 I slot print_timing: id 2 | task 9300 | graph reallocs = 0 / 0 (same size) / (changed size) 66.34.260.056 I slot release: id 2 | task 9300 | stop processing: n_tokens = 2026, truncated = 0 66.34.260.243 I slot print_timing: id 3 | task 9303 | prompt eval time = 14216.51 ms / 413 tokens ( 34.42 ms per token, 29.05 tokens per second) 66.34.260.246 I slot print_timing: id 3 | task 9303 | eval time = 214.42 ms / 2 tokens ( 214.42 ms per token, 4.66 tokens per second) 66.34.260.247 I slot print_timing: id 3 | task 9303 | total time = 14430.94 ms / 415 tokens 66.34.260.247 I slot print_timing: id 3 | task 9303 | graphs reused = 7887 66.34.260.247 I slot print_timing: id 3 | task 9303 | graph reallocs = 0 / 0 (same size) / (changed size) 66.34.260.291 I slot release: id 3 | task 9303 | stop processing: n_tokens = 2175, truncated = 0 66.34.270.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 82790001450 66.34.270.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 66.34.291.780 I slot launch_slot_: id 0 | task 9307 | processing task, is_child = 0 66.34.291.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 882.055 MiB) 66.34.312.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.427 MiB) 66.34.333.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.551 MiB) 66.34.385.722 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.880 66.34.385.803 I slot launch_slot_: id 1 | task 9308 | processing task, is_child = 0 66.34.386.013 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.883 66.34.386.046 I slot launch_slot_: id 2 | task 9309 | processing task, is_child = 0 66.34.386.148 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.823 66.34.386.168 I slot launch_slot_: id 3 | task 9310 | processing task, is_child = 0 66.44.738.425 I slot print_timing: id 0 | task 9307 | prompt processing, n_tokens = 363, progress = 0.25, t = 10.35 s / 35.06 tokens per second 66.45.895.725 I slot print_timing: id 1 | task 9308 | prompt processing, n_tokens = 192, progress = 1.00, t = 10.35 s / 18.55 tokens per second 66.45.900.339 I slot print_timing: id 2 | task 9309 | prompt processing, n_tokens = 145, progress = 1.00, t = 10.34 s / 14.02 tokens per second 66.45.904.941 I slot print_timing: id 3 | task 9310 | prompt processing, n_tokens = 226, progress = 1.00, t = 10.34 s / 21.87 tokens per second 66.48.827.141 I slot print_timing: id 0 | task 9307 | prompt processing, n_tokens = 575, progress = 0.39, t = 14.44 s / 39.82 tokens per second 66.53.309.015 I slot print_timing: id 1 | task 9308 | prompt eval time = 14440.38 ms / 196 tokens ( 73.68 ms per token, 13.57 tokens per second) 66.53.309.020 I slot print_timing: id 1 | task 9308 | eval time = 4482.30 ms / 2 tokens ( 4482.30 ms per token, 0.22 tokens per second) 66.53.309.020 I slot print_timing: id 1 | task 9308 | total time = 18922.68 ms / 198 tokens 66.53.309.021 I slot print_timing: id 1 | task 9308 | graphs reused = 7887 66.53.309.021 I slot print_timing: id 1 | task 9308 | graph reallocs = 0 / 0 (same size) / (changed size) 66.53.309.093 I slot release: id 1 | task 9308 | stop processing: n_tokens = 1958, truncated = 0 66.53.309.267 I slot print_timing: id 2 | task 9309 | prompt eval time = 14432.41 ms / 149 tokens ( 96.86 ms per token, 10.32 tokens per second) 66.53.309.274 I slot print_timing: id 2 | task 9309 | eval time = 4482.34 ms / 2 tokens ( 4482.34 ms per token, 0.22 tokens per second) 66.53.309.274 I slot print_timing: id 2 | task 9309 | total time = 18914.75 ms / 151 tokens 66.53.309.275 I slot print_timing: id 2 | task 9309 | graphs reused = 7887 66.53.309.275 I slot print_timing: id 2 | task 9309 | graph reallocs = 0 / 0 (same size) / (changed size) 66.53.309.328 I slot release: id 2 | task 9309 | stop processing: n_tokens = 1911, truncated = 0 66.53.309.573 I slot print_timing: id 3 | task 9310 | prompt eval time = 14424.74 ms / 230 tokens ( 62.72 ms per token, 15.94 tokens per second) 66.53.309.575 I slot print_timing: id 3 | task 9310 | eval time = 4482.44 ms / 2 tokens ( 4482.44 ms per token, 0.22 tokens per second) 66.53.309.575 I slot print_timing: id 3 | task 9310 | total time = 18907.18 ms / 232 tokens 66.53.309.576 I slot print_timing: id 3 | task 9310 | graphs reused = 7887 66.53.309.576 I slot print_timing: id 3 | task 9310 | graph reallocs = 0 / 0 (same size) / (changed size) 66.53.309.629 I slot release: id 3 | task 9310 | stop processing: n_tokens = 1992, truncated = 0 66.53.309.639 I slot print_timing: id 0 | task 9307 | prompt processing, n_tokens = 959, progress = 0.65, t = 18.92 s / 50.68 tokens per second 66.53.321.630 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 82809050898 66.53.321.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.303 MiB) 66.56.987.218 I slot launch_slot_: id 1 | task 9315 | processing task, is_child = 0 66.56.987.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.867 MiB) 66.57.009.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 883.618 MiB) 66.57.029.704 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 82809051133 66.57.029.854 I slot launch_slot_: id 2 | task 9316 | processing task, is_child = 0 66.57.029.941 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 82809051435 66.57.030.049 I slot launch_slot_: id 3 | task 9317 | processing task, is_child = 0 66.57.030.056 I slot print_timing: id 0 | task 9307 | prompt processing, n_tokens = 1275, progress = 0.86, t = 18.94 s / 67.33 tokens per second 67.08.645.585 I slot print_timing: id 0 | task 9307 | prompt processing, n_tokens = 1471, progress = 1.00, t = 34.26 s / 42.94 tokens per second 67.11.206.154 I slot print_timing: id 1 | task 9315 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.61 s / 22.48 tokens per second 67.11.210.594 I slot print_timing: id 2 | task 9316 | prompt processing, n_tokens = 363, progress = 0.23, t = 11.61 s / 31.26 tokens per second 67.11.217.951 I slot print_timing: id 3 | task 9317 | prompt processing, n_tokens = 363, progress = 0.22, t = 11.61 s / 31.26 tokens per second 67.18.118.158 I slot print_timing: id 1 | task 9315 | prompt processing, n_tokens = 409, progress = 0.41, t = 21.08 s / 19.40 tokens per second 67.18.118.172 I slot print_timing: id 2 | task 9316 | prompt processing, n_tokens = 575, progress = 0.37, t = 21.08 s / 27.27 tokens per second 67.18.118.184 I slot print_timing: id 3 | task 9317 | prompt processing, n_tokens = 575, progress = 0.34, t = 21.08 s / 27.27 tokens per second 67.31.428.357 I slot print_timing: id 0 | task 9307 | prompt eval time = 43731.97 ms / 1475 tokens ( 29.65 ms per token, 33.73 tokens per second) 67.31.428.361 I slot print_timing: id 0 | task 9307 | eval time = 13310.20 ms / 2 tokens (13310.20 ms per token, 0.08 tokens per second) 67.31.428.361 I slot print_timing: id 0 | task 9307 | total time = 57042.17 ms / 1477 tokens 67.31.428.362 I slot print_timing: id 0 | task 9307 | graphs reused = 7887 67.31.428.362 I slot print_timing: id 0 | task 9307 | graph reallocs = 0 / 0 (same size) / (changed size) 67.31.428.436 I slot release: id 0 | task 9307 | stop processing: n_tokens = 1476, truncated = 0 67.31.428.453 I slot print_timing: id 1 | task 9315 | prompt processing, n_tokens = 483, progress = 0.48, t = 34.39 s / 14.04 tokens per second 67.31.439.497 I slot print_timing: id 2 | task 9316 | prompt processing, n_tokens = 1039, progress = 0.67, t = 34.39 s / 30.21 tokens per second 67.31.444.487 I slot print_timing: id 3 | task 9317 | prompt processing, n_tokens = 1161, progress = 0.69, t = 34.39 s / 33.76 tokens per second 67.38.386.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 82847170241 67.38.386.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.303 MiB) 67.40.217.019 I slot launch_slot_: id 0 | task 9322 | processing task, is_child = 0 67.40.217.143 I slot print_timing: id 1 | task 9315 | prompt processing, n_tokens = 853, progress = 0.85, t = 41.35 s / 20.63 tokens per second 67.40.221.565 I slot print_timing: id 2 | task 9316 | prompt processing, n_tokens = 1275, progress = 0.82, t = 41.35 s / 30.83 tokens per second 67.40.225.973 I slot print_timing: id 3 | task 9317 | prompt processing, n_tokens = 1275, progress = 0.76, t = 41.35 s / 30.83 tokens per second 67.51.580.544 I slot print_timing: id 0 | task 9322 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.36 s / 22.97 tokens per second 67.53.084.792 I slot print_timing: id 1 | task 9315 | prompt processing, n_tokens = 995, progress = 1.00, t = 54.55 s / 18.24 tokens per second 67.53.094.158 I slot print_timing: id 2 | task 9316 | prompt processing, n_tokens = 1551, progress = 1.00, t = 54.55 s / 28.43 tokens per second 67.53.100.601 I slot print_timing: id 3 | task 9317 | prompt processing, n_tokens = 1673, progress = 1.00, t = 54.55 s / 30.67 tokens per second 67.55.298.553 I slot print_timing: id 0 | task 9322 | prompt processing, n_tokens = 409, progress = 0.41, t = 15.08 s / 27.12 tokens per second 67.56.270.417 I slot print_timing: id 1 | task 9315 | prompt eval time = 58263.43 ms / 999 tokens ( 58.32 ms per token, 17.15 tokens per second) 67.56.270.419 I slot print_timing: id 1 | task 9315 | eval time = 972.49 ms / 2 tokens ( 972.49 ms per token, 1.03 tokens per second) 67.56.270.419 I slot print_timing: id 1 | task 9315 | total time = 59235.91 ms / 1001 tokens 67.56.270.420 I slot print_timing: id 1 | task 9315 | graphs reused = 7887 67.56.270.420 I slot print_timing: id 1 | task 9315 | graph reallocs = 0 / 0 (same size) / (changed size) 67.56.270.471 I slot release: id 1 | task 9315 | stop processing: n_tokens = 1000, truncated = 0 67.56.270.623 I slot print_timing: id 2 | task 9316 | prompt eval time = 58263.51 ms / 1555 tokens ( 37.47 ms per token, 26.69 tokens per second) 67.56.270.625 I slot print_timing: id 2 | task 9316 | eval time = 972.47 ms / 2 tokens ( 972.47 ms per token, 1.03 tokens per second) 67.56.270.626 I slot print_timing: id 2 | task 9316 | total time = 59235.98 ms / 1557 tokens 67.56.270.626 I slot print_timing: id 2 | task 9316 | graphs reused = 7887 67.56.270.626 I slot print_timing: id 2 | task 9316 | graph reallocs = 0 / 0 (same size) / (changed size) 67.56.270.687 I slot release: id 2 | task 9316 | stop processing: n_tokens = 1556, truncated = 0 67.56.271.033 I slot print_timing: id 3 | task 9317 | prompt eval time = 58263.75 ms / 1677 tokens ( 34.74 ms per token, 28.78 tokens per second) 67.56.271.036 I slot print_timing: id 3 | task 9317 | eval time = 972.49 ms / 2 tokens ( 972.49 ms per token, 1.03 tokens per second) 67.56.271.036 I slot print_timing: id 3 | task 9317 | total time = 59236.25 ms / 1679 tokens 67.56.271.036 I slot print_timing: id 3 | task 9317 | graphs reused = 7887 67.56.271.037 I slot print_timing: id 3 | task 9317 | graph reallocs = 0 / 0 (same size) / (changed size) 67.56.271.077 I slot release: id 3 | task 9317 | stop processing: n_tokens = 1678, truncated = 0 67.56.271.085 I slot print_timing: id 0 | task 9322 | prompt processing, n_tokens = 473, progress = 0.48, t = 16.05 s / 29.46 tokens per second 67.56.282.642 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 67.56.282.683 I slot launch_slot_: id 1 | task 9327 | processing task, is_child = 0 67.56.282.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 68.00.603.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 873.052 MiB) 68.00.626.680 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 82872012492 68.00.626.829 I slot launch_slot_: id 2 | task 9328 | processing task, is_child = 0 68.00.626.901 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 82872012882 68.00.626.991 I slot launch_slot_: id 3 | task 9329 | processing task, is_child = 0 68.00.626.999 I slot print_timing: id 0 | task 9322 | prompt processing, n_tokens = 853, progress = 0.86, t = 16.07 s / 53.09 tokens per second 68.05.835.492 I slot print_timing: id 0 | task 9322 | prompt processing, n_tokens = 985, progress = 1.00, t = 25.62 s / 38.45 tokens per second 68.09.446.501 I slot print_timing: id 1 | task 9327 | prompt processing, n_tokens = 103, progress = 1.00, t = 5.20 s / 19.79 tokens per second 68.09.451.046 I slot print_timing: id 2 | task 9328 | prompt processing, n_tokens = 261, progress = 0.27, t = 5.20 s / 50.23 tokens per second 68.09.455.420 I slot print_timing: id 3 | task 9329 | prompt processing, n_tokens = 261, progress = 0.27, t = 5.20 s / 50.23 tokens per second 68.13.075.554 I slot print_timing: id 2 | task 9328 | prompt processing, n_tokens = 409, progress = 0.42, t = 12.44 s / 32.89 tokens per second 68.13.075.565 I slot print_timing: id 3 | task 9329 | prompt processing, n_tokens = 409, progress = 0.42, t = 12.44 s / 32.89 tokens per second 68.14.928.112 I slot print_timing: id 0 | task 9322 | prompt eval time = 32858.32 ms / 989 tokens ( 33.22 ms per token, 30.10 tokens per second) 68.14.928.115 I slot print_timing: id 0 | task 9322 | eval time = 1852.75 ms / 2 tokens ( 1852.75 ms per token, 0.54 tokens per second) 68.14.928.128 I slot print_timing: id 0 | task 9322 | total time = 34711.07 ms / 991 tokens 68.14.928.131 I slot print_timing: id 0 | task 9322 | graphs reused = 7887 68.14.928.131 I slot print_timing: id 0 | task 9322 | graph reallocs = 0 / 0 (same size) / (changed size) 68.14.928.176 I slot release: id 0 | task 9322 | stop processing: n_tokens = 990, truncated = 0 68.14.928.330 I slot print_timing: id 1 | task 9327 | prompt eval time = 12444.09 ms / 107 tokens ( 116.30 ms per token, 8.60 tokens per second) 68.14.928.332 I slot print_timing: id 1 | task 9327 | eval time = 1852.79 ms / 2 tokens ( 1852.79 ms per token, 0.54 tokens per second) 68.14.928.333 I slot print_timing: id 1 | task 9327 | total time = 14296.88 ms / 109 tokens 68.14.928.333 I slot print_timing: id 1 | task 9327 | graphs reused = 7887 68.14.928.334 I slot print_timing: id 1 | task 9327 | graph reallocs = 0 / 0 (same size) / (changed size) 68.14.928.360 I slot release: id 1 | task 9327 | stop processing: n_tokens = 961, truncated = 0 68.14.928.369 I slot print_timing: id 2 | task 9328 | prompt processing, n_tokens = 461, progress = 0.47, t = 14.29 s / 32.26 tokens per second 68.14.934.284 I slot print_timing: id 3 | task 9329 | prompt processing, n_tokens = 467, progress = 0.48, t = 14.29 s / 32.68 tokens per second 68.23.924.843 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 68.23.924.922 I slot launch_slot_: id 0 | task 9334 | processing task, is_child = 0 68.23.924.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.303 MiB) 68.24.104.196 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.917 68.24.104.274 I slot launch_slot_: id 1 | task 9335 | processing task, is_child = 0 68.24.119.389 I slot print_timing: id 2 | task 9328 | prompt processing, n_tokens = 853, progress = 0.87, t = 23.29 s / 36.63 tokens per second 68.24.123.831 I slot print_timing: id 3 | task 9329 | prompt processing, n_tokens = 853, progress = 0.87, t = 23.29 s / 36.63 tokens per second 68.30.077.661 I slot print_timing: id 0 | task 9334 | prompt processing, n_tokens = 115, progress = 1.00, t = 5.97 s / 19.25 tokens per second 68.30.257.869 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 119, progress = 1.00, t = 5.97 s / 19.95 tokens per second 68.30.262.358 I slot print_timing: id 2 | task 9328 | prompt processing, n_tokens = 973, progress = 1.00, t = 29.44 s / 33.05 tokens per second 68.30.266.858 I slot print_timing: id 3 | task 9329 | prompt processing, n_tokens = 979, progress = 1.00, t = 29.44 s / 33.26 tokens per second 68.30.860.052 I slot print_timing: id 0 | task 9334 | prompt eval time = 6543.59 ms / 119 tokens ( 54.99 ms per token, 18.19 tokens per second) 68.30.860.055 I slot print_timing: id 0 | task 9334 | eval time = 212.18 ms / 2 tokens ( 212.18 ms per token, 4.71 tokens per second) 68.30.860.055 I slot print_timing: id 0 | task 9334 | total time = 6755.77 ms / 121 tokens 68.30.860.056 I slot print_timing: id 0 | task 9334 | graphs reused = 7887 68.30.860.056 I slot print_timing: id 0 | task 9334 | graph reallocs = 0 / 0 (same size) / (changed size) 68.30.860.099 I slot release: id 0 | task 9334 | stop processing: n_tokens = 973, truncated = 0 68.30.860.246 I slot print_timing: id 1 | task 9335 | prompt eval time = 6536.19 ms / 123 tokens ( 53.14 ms per token, 18.82 tokens per second) 68.30.860.251 I slot print_timing: id 1 | task 9335 | eval time = 212.22 ms / 2 tokens ( 212.22 ms per token, 4.71 tokens per second) 68.30.860.252 I slot print_timing: id 1 | task 9335 | total time = 6748.41 ms / 125 tokens 68.30.860.252 I slot print_timing: id 1 | task 9335 | graphs reused = 7887 68.30.860.252 I slot print_timing: id 1 | task 9335 | graph reallocs = 0 / 0 (same size) / (changed size) 68.30.860.280 I slot release: id 1 | task 9335 | stop processing: n_tokens = 977, truncated = 0 68.30.860.441 I slot print_timing: id 2 | task 9328 | prompt eval time = 30009.15 ms / 977 tokens ( 30.72 ms per token, 32.56 tokens per second) 68.30.860.443 I slot print_timing: id 2 | task 9328 | eval time = 212.25 ms / 2 tokens ( 212.25 ms per token, 4.71 tokens per second) 68.30.860.444 I slot print_timing: id 2 | task 9328 | total time = 30221.40 ms / 979 tokens 68.30.860.444 I slot print_timing: id 2 | task 9328 | graphs reused = 7887 68.30.860.444 I slot print_timing: id 2 | task 9328 | graph reallocs = 0 / 0 (same size) / (changed size) 68.30.860.478 I slot release: id 2 | task 9328 | stop processing: n_tokens = 978, truncated = 0 68.30.860.638 I slot print_timing: id 3 | task 9329 | prompt eval time = 30009.42 ms / 983 tokens ( 30.53 ms per token, 32.76 tokens per second) 68.30.860.640 I slot print_timing: id 3 | task 9329 | eval time = 212.06 ms / 2 tokens ( 212.06 ms per token, 4.72 tokens per second) 68.30.860.641 I slot print_timing: id 3 | task 9329 | total time = 30221.48 ms / 985 tokens 68.30.860.641 I slot print_timing: id 3 | task 9329 | graphs reused = 7887 68.30.860.641 I slot print_timing: id 3 | task 9329 | graph reallocs = 0 / 0 (same size) / (changed size) 68.30.860.661 I slot release: id 3 | task 9329 | stop processing: n_tokens = 984, truncated = 0 68.30.869.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 82906601904 68.30.869.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.802 MiB) 68.30.888.805 I slot launch_slot_: id 0 | task 9339 | processing task, is_child = 0 68.30.888.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 884.118 MiB) 68.30.907.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.551 MiB) 68.30.926.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 867.612 MiB) 68.30.946.019 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 82906602085 68.30.946.122 I slot launch_slot_: id 1 | task 9340 | processing task, is_child = 0 68.30.946.219 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 82906602283 68.30.946.284 I slot launch_slot_: id 2 | task 9341 | processing task, is_child = 0 68.30.946.332 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 82906602466 68.30.946.395 I slot launch_slot_: id 3 | task 9342 | processing task, is_child = 0 68.44.325.946 I slot print_timing: id 0 | task 9339 | prompt processing, n_tokens = 166, progress = 0.20, t = 13.38 s / 12.41 tokens per second 68.45.110.627 I slot print_timing: id 1 | task 9340 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.38 s / 26.31 tokens per second 68.45.115.565 I slot print_timing: id 2 | task 9341 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.38 s / 26.31 tokens per second 68.45.120.202 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.38 s / 26.31 tokens per second 68.51.644.242 I slot print_timing: id 0 | task 9339 | prompt processing, n_tokens = 309, progress = 0.37, t = 20.70 s / 14.93 tokens per second 68.53.171.267 I slot print_timing: id 1 | task 9340 | prompt processing, n_tokens = 533, progress = 0.34, t = 20.70 s / 25.75 tokens per second 68.53.171.288 I slot print_timing: id 2 | task 9341 | prompt processing, n_tokens = 533, progress = 0.33, t = 20.70 s / 25.75 tokens per second 68.53.171.300 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 533, progress = 0.33, t = 20.70 s / 25.75 tokens per second 69.16.657.221 I slot print_timing: id 0 | task 9339 | prompt processing, n_tokens = 706, progress = 0.86, t = 45.71 s / 15.44 tokens per second 69.17.093.221 I slot print_timing: id 1 | task 9340 | prompt processing, n_tokens = 1071, progress = 0.67, t = 45.71 s / 23.43 tokens per second 69.17.097.806 I slot print_timing: id 2 | task 9341 | prompt processing, n_tokens = 1099, progress = 0.68, t = 45.71 s / 24.04 tokens per second 69.17.102.505 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 1080, progress = 0.66, t = 45.71 s / 23.63 tokens per second 69.25.567.164 I slot print_timing: id 0 | task 9339 | prompt processing, n_tokens = 821, progress = 1.00, t = 54.62 s / 15.03 tokens per second 69.26.005.927 I slot print_timing: id 1 | task 9340 | prompt processing, n_tokens = 1374, progress = 0.87, t = 54.62 s / 25.16 tokens per second 69.26.010.337 I slot print_timing: id 2 | task 9341 | prompt processing, n_tokens = 1374, progress = 0.85, t = 54.62 s / 25.16 tokens per second 69.26.014.731 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 1113, progress = 0.68, t = 54.62 s / 20.38 tokens per second 69.35.010.696 I slot print_timing: id 1 | task 9340 | prompt processing, n_tokens = 1583, progress = 1.00, t = 64.06 s / 24.71 tokens per second 69.35.019.127 I slot print_timing: id 2 | task 9341 | prompt processing, n_tokens = 1611, progress = 1.00, t = 64.06 s / 25.15 tokens per second 69.35.023.688 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 1374, progress = 0.84, t = 64.06 s / 21.45 tokens per second 69.38.494.031 I slot print_timing: id 0 | task 9339 | prompt eval time = 64064.28 ms / 825 tokens ( 77.65 ms per token, 12.88 tokens per second) 69.38.494.034 I slot print_timing: id 0 | task 9339 | eval time = 3483.34 ms / 2 tokens ( 3483.34 ms per token, 0.29 tokens per second) 69.38.494.035 I slot print_timing: id 0 | task 9339 | total time = 67547.62 ms / 827 tokens 69.38.494.035 I slot print_timing: id 0 | task 9339 | graphs reused = 7888 69.38.494.036 I slot print_timing: id 0 | task 9339 | graph reallocs = 0 / 0 (same size) / (changed size) 69.38.494.077 I slot release: id 0 | task 9339 | stop processing: n_tokens = 826, truncated = 0 69.38.494.598 I slot print_timing: id 3 | task 9342 | prompt processing, n_tokens = 1625, progress = 1.00, t = 67.55 s / 24.06 tokens per second 69.38.878.182 I slot print_timing: id 1 | task 9340 | prompt eval time = 67547.87 ms / 1587 tokens ( 42.56 ms per token, 23.49 tokens per second) 69.38.878.187 I slot print_timing: id 1 | task 9340 | eval time = 383.83 ms / 2 tokens ( 383.83 ms per token, 2.61 tokens per second) 69.38.878.188 I slot print_timing: id 1 | task 9340 | total time = 67931.70 ms / 1589 tokens 69.38.878.189 I slot print_timing: id 1 | task 9340 | graphs reused = 7888 69.38.878.189 I slot print_timing: id 1 | task 9340 | graph reallocs = 0 / 0 (same size) / (changed size) 69.38.878.258 I slot release: id 1 | task 9340 | stop processing: n_tokens = 1588, truncated = 0 69.38.878.403 I slot print_timing: id 2 | task 9341 | prompt eval time = 67548.04 ms / 1615 tokens ( 41.83 ms per token, 23.91 tokens per second) 69.38.878.406 I slot print_timing: id 2 | task 9341 | eval time = 383.81 ms / 2 tokens ( 383.81 ms per token, 2.61 tokens per second) 69.38.878.406 I slot print_timing: id 2 | task 9341 | total time = 67931.85 ms / 1617 tokens 69.38.878.406 I slot print_timing: id 2 | task 9341 | graphs reused = 7888 69.38.878.407 I slot print_timing: id 2 | task 9341 | graph reallocs = 0 / 0 (same size) / (changed size) 69.38.878.447 I slot release: id 2 | task 9341 | stop processing: n_tokens = 1616, truncated = 0 69.38.878.641 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.883 69.38.878.696 I slot launch_slot_: id 1 | task 9350 | processing task, is_child = 0 69.38.878.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 872.677 MiB) 69.38.899.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 840.415 MiB) 69.38.919.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 82974235882 69.38.919.232 I slot launch_slot_: id 0 | task 9351 | processing task, is_child = 0 69.38.919.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.868 69.38.919.339 I slot launch_slot_: id 2 | task 9352 | processing task, is_child = 0 69.47.477.133 I slot print_timing: id 3 | task 9342 | prompt eval time = 67932.01 ms / 1629 tokens ( 41.70 ms per token, 23.98 tokens per second) 69.47.477.136 I slot print_timing: id 3 | task 9342 | eval time = 8598.49 ms / 2 tokens ( 8598.49 ms per token, 0.12 tokens per second) 69.47.477.136 I slot print_timing: id 3 | task 9342 | total time = 76530.50 ms / 1631 tokens 69.47.477.137 I slot print_timing: id 3 | task 9342 | graphs reused = 7888 69.47.477.137 I slot print_timing: id 3 | task 9342 | graph reallocs = 0 / 0 (same size) / (changed size) 69.47.477.204 I slot release: id 3 | task 9342 | stop processing: n_tokens = 1630, truncated = 0 69.47.477.217 I slot print_timing: id 0 | task 9351 | prompt processing, n_tokens = 126, progress = 0.15, t = 8.56 s / 14.72 tokens per second 69.47.482.965 I slot print_timing: id 1 | task 9350 | prompt processing, n_tokens = 251, progress = 1.00, t = 8.56 s / 29.33 tokens per second 69.47.487.891 I slot print_timing: id 2 | task 9352 | prompt processing, n_tokens = 340, progress = 1.00, t = 8.55 s / 39.77 tokens per second 69.49.307.613 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 82983219010 69.49.307.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 845.417 MiB) 69.49.331.982 I slot launch_slot_: id 3 | task 9355 | processing task, is_child = 0 69.49.331.994 I slot print_timing: id 0 | task 9351 | prompt processing, n_tokens = 245, progress = 0.29, t = 10.39 s / 23.59 tokens per second 69.52.137.045 I slot print_timing: id 1 | task 9350 | prompt eval time = 10387.95 ms / 255 tokens ( 40.74 ms per token, 24.55 tokens per second) 69.52.137.050 I slot print_timing: id 1 | task 9350 | eval time = 2829.66 ms / 2 tokens ( 2829.66 ms per token, 0.35 tokens per second) 69.52.137.051 I slot print_timing: id 1 | task 9350 | total time = 13217.60 ms / 257 tokens 69.52.137.052 I slot print_timing: id 1 | task 9350 | graphs reused = 7888 69.52.137.052 I slot print_timing: id 1 | task 9350 | graph reallocs = 0 / 0 (same size) / (changed size) 69.52.137.116 I slot release: id 1 | task 9350 | stop processing: n_tokens = 1630, truncated = 0 69.52.137.353 I slot print_timing: id 2 | task 9352 | prompt eval time = 10380.59 ms / 344 tokens ( 30.18 ms per token, 33.14 tokens per second) 69.52.137.356 I slot print_timing: id 2 | task 9352 | eval time = 2829.74 ms / 2 tokens ( 2829.74 ms per token, 0.35 tokens per second) 69.52.137.356 I slot print_timing: id 2 | task 9352 | total time = 13210.34 ms / 346 tokens 69.52.137.356 I slot print_timing: id 2 | task 9352 | graphs reused = 7888 69.52.137.357 I slot print_timing: id 2 | task 9352 | graph reallocs = 0 / 0 (same size) / (changed size) 69.52.137.410 I slot release: id 2 | task 9352 | stop processing: n_tokens = 1719, truncated = 0 69.52.137.417 I slot print_timing: id 0 | task 9351 | prompt processing, n_tokens = 322, progress = 0.38, t = 13.22 s / 24.36 tokens per second 69.56.827.019 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 82987878921 69.56.827.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 853.044 MiB) 69.58.302.458 I slot launch_slot_: id 1 | task 9358 | processing task, is_child = 0 69.58.302.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.216 MiB) 69.58.323.843 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 82987879215 69.58.323.971 I slot launch_slot_: id 2 | task 9359 | processing task, is_child = 0 69.58.323.979 I slot print_timing: id 0 | task 9351 | prompt processing, n_tokens = 725, progress = 0.87, t = 17.91 s / 40.49 tokens per second 69.58.328.634 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 245, progress = 0.28, t = 7.50 s / 32.69 tokens per second 70.03.362.535 I slot print_timing: id 0 | task 9351 | prompt processing, n_tokens = 834, progress = 1.00, t = 24.44 s / 34.12 tokens per second 70.04.520.121 I slot print_timing: id 1 | task 9358 | prompt processing, n_tokens = 149, progress = 0.18, t = 5.03 s / 29.60 tokens per second 70.04.524.551 I slot print_timing: id 2 | task 9359 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.03 s / 29.60 tokens per second 70.04.529.271 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 349, progress = 0.40, t = 14.03 s / 24.87 tokens per second 70.12.089.324 I slot print_timing: id 1 | task 9358 | prompt processing, n_tokens = 277, progress = 0.33, t = 13.76 s / 20.13 tokens per second 70.12.089.337 I slot print_timing: id 2 | task 9359 | prompt processing, n_tokens = 277, progress = 0.32, t = 13.76 s / 20.13 tokens per second 70.12.089.343 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 725, progress = 0.84, t = 22.76 s / 31.86 tokens per second 70.16.056.307 I slot print_timing: id 0 | task 9351 | prompt eval time = 33169.97 ms / 838 tokens ( 39.58 ms per token, 25.26 tokens per second) 70.16.056.311 I slot print_timing: id 0 | task 9351 | eval time = 3966.99 ms / 2 tokens ( 3966.99 ms per token, 0.25 tokens per second) 70.16.056.312 I slot print_timing: id 0 | task 9351 | total time = 37136.95 ms / 840 tokens 70.16.056.312 I slot print_timing: id 0 | task 9351 | graphs reused = 7888 70.16.056.313 I slot print_timing: id 0 | task 9351 | graph reallocs = 0 / 0 (same size) / (changed size) 70.16.056.357 I slot release: id 0 | task 9351 | stop processing: n_tokens = 839, truncated = 0 70.16.056.368 I slot print_timing: id 1 | task 9358 | prompt processing, n_tokens = 326, progress = 0.39, t = 17.73 s / 18.39 tokens per second 70.16.061.599 I slot print_timing: id 2 | task 9359 | prompt processing, n_tokens = 343, progress = 0.40, t = 17.73 s / 19.35 tokens per second 70.16.066.330 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 861, progress = 1.00, t = 26.72 s / 32.22 tokens per second 70.25.409.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 83011798162 70.25.409.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.966 MiB) 70.25.429.037 I slot launch_slot_: id 0 | task 9364 | processing task, is_child = 0 70.25.429.117 I slot print_timing: id 1 | task 9358 | prompt processing, n_tokens = 716, progress = 0.85, t = 27.08 s / 26.44 tokens per second 70.25.433.826 I slot print_timing: id 2 | task 9359 | prompt processing, n_tokens = 716, progress = 0.83, t = 27.08 s / 26.44 tokens per second 70.30.708.545 I slot print_timing: id 3 | task 9355 | prompt eval time = 36077.86 ms / 865 tokens ( 41.71 ms per token, 23.98 tokens per second) 70.30.708.548 I slot print_timing: id 3 | task 9355 | eval time = 5298.67 ms / 2 tokens ( 5298.67 ms per token, 0.19 tokens per second) 70.30.708.548 I slot print_timing: id 3 | task 9355 | total time = 41376.53 ms / 867 tokens 70.30.708.549 I slot print_timing: id 3 | task 9355 | graphs reused = 7888 70.30.708.549 I slot print_timing: id 3 | task 9355 | graph reallocs = 0 / 0 (same size) / (changed size) 70.30.708.591 I slot release: id 3 | task 9355 | stop processing: n_tokens = 866, truncated = 0 70.30.708.602 I slot print_timing: id 0 | task 9364 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.28 s / 28.22 tokens per second 70.30.715.280 I slot print_timing: id 1 | task 9358 | prompt processing, n_tokens = 838, progress = 1.00, t = 32.38 s / 25.88 tokens per second 70.30.719.784 I slot print_timing: id 2 | task 9359 | prompt processing, n_tokens = 855, progress = 1.00, t = 32.38 s / 26.41 tokens per second 70.32.542.258 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 83026450396 70.32.542.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.216 MiB) 70.32.563.382 I slot launch_slot_: id 3 | task 9367 | processing task, is_child = 0 70.32.563.394 I slot print_timing: id 0 | task 9364 | prompt processing, n_tokens = 277, progress = 0.31, t = 7.11 s / 38.94 tokens per second 70.35.374.456 I slot print_timing: id 1 | task 9358 | prompt eval time = 34213.64 ms / 842 tokens ( 40.63 ms per token, 24.61 tokens per second) 70.35.374.458 I slot print_timing: id 1 | task 9358 | eval time = 2832.41 ms / 2 tokens ( 2832.41 ms per token, 0.35 tokens per second) 70.35.374.459 I slot print_timing: id 1 | task 9358 | total time = 37046.05 ms / 844 tokens 70.35.374.459 I slot print_timing: id 1 | task 9358 | graphs reused = 7888 70.35.374.460 I slot print_timing: id 1 | task 9358 | graph reallocs = 0 / 0 (same size) / (changed size) 70.35.374.501 I slot release: id 1 | task 9358 | stop processing: n_tokens = 843, truncated = 0 70.35.374.709 I slot print_timing: id 2 | task 9359 | prompt eval time = 34213.72 ms / 859 tokens ( 39.83 ms per token, 25.11 tokens per second) 70.35.374.711 I slot print_timing: id 2 | task 9359 | eval time = 2832.46 ms / 2 tokens ( 2832.46 ms per token, 0.35 tokens per second) 70.35.374.711 I slot print_timing: id 2 | task 9359 | total time = 37046.18 ms / 861 tokens 70.35.374.712 I slot print_timing: id 2 | task 9359 | graphs reused = 7888 70.35.374.712 I slot print_timing: id 2 | task 9359 | graph reallocs = 0 / 0 (same size) / (changed size) 70.35.374.740 I slot release: id 2 | task 9359 | stop processing: n_tokens = 860, truncated = 0 70.35.374.747 I slot print_timing: id 0 | task 9364 | prompt processing, n_tokens = 370, progress = 0.42, t = 9.95 s / 37.20 tokens per second 70.39.371.438 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 83031116306 70.39.371.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.278 MiB) 70.41.191.214 I slot launch_slot_: id 1 | task 9370 | processing task, is_child = 0 70.41.191.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.654 MiB) 70.41.210.154 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 83031116545 70.41.210.248 I slot launch_slot_: id 2 | task 9371 | processing task, is_child = 0 70.41.210.256 I slot print_timing: id 0 | task 9364 | prompt processing, n_tokens = 716, progress = 0.81, t = 13.94 s / 51.35 tokens per second 70.41.214.916 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 260, progress = 0.33, t = 6.81 s / 38.19 tokens per second 70.46.325.326 I slot print_timing: id 0 | task 9364 | prompt processing, n_tokens = 882, progress = 1.00, t = 20.90 s / 42.21 tokens per second 70.46.625.327 I slot print_timing: id 1 | task 9370 | prompt processing, n_tokens = 113, progress = 0.16, t = 5.11 s / 22.11 tokens per second 70.46.629.737 I slot print_timing: id 2 | task 9371 | prompt processing, n_tokens = 125, progress = 0.17, t = 5.11 s / 24.46 tokens per second 70.46.634.158 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 264, progress = 0.34, t = 13.76 s / 19.18 tokens per second 70.53.217.490 I slot print_timing: id 1 | task 9370 | prompt processing, n_tokens = 175, progress = 0.25, t = 12.00 s / 14.58 tokens per second 70.53.223.907 I slot print_timing: id 2 | task 9371 | prompt processing, n_tokens = 233, progress = 0.31, t = 12.00 s / 19.41 tokens per second 70.53.228.377 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 628, progress = 0.81, t = 20.65 s / 30.41 tokens per second 71.04.340.728 I slot print_timing: id 0 | task 9364 | prompt eval time = 27788.43 ms / 886 tokens ( 31.36 ms per token, 31.88 tokens per second) 71.04.340.731 I slot print_timing: id 0 | task 9364 | eval time = 11123.24 ms / 2 tokens (11123.24 ms per token, 0.09 tokens per second) 71.04.340.731 I slot print_timing: id 0 | task 9364 | total time = 38911.67 ms / 888 tokens 71.04.340.732 I slot print_timing: id 0 | task 9364 | graphs reused = 7888 71.04.340.732 I slot print_timing: id 0 | task 9364 | graph reallocs = 0 / 0 (same size) / (changed size) 71.04.340.774 I slot release: id 0 | task 9364 | stop processing: n_tokens = 887, truncated = 0 71.04.340.787 I slot print_timing: id 1 | task 9370 | prompt processing, n_tokens = 571, progress = 0.83, t = 23.13 s / 24.69 tokens per second 71.04.346.439 I slot print_timing: id 2 | task 9371 | prompt processing, n_tokens = 628, progress = 0.84, t = 23.13 s / 27.16 tokens per second 71.04.351.272 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 776, progress = 0.99, t = 31.78 s / 24.42 tokens per second 71.07.347.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 83060082579 71.07.347.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 71.07.367.742 I slot launch_slot_: id 0 | task 9376 | processing task, is_child = 0 71.07.367.828 I slot print_timing: id 1 | task 9370 | prompt processing, n_tokens = 687, progress = 0.99, t = 26.13 s / 26.29 tokens per second 71.07.372.308 I slot print_timing: id 2 | task 9371 | prompt processing, n_tokens = 745, progress = 0.99, t = 26.13 s / 28.51 tokens per second 71.09.275.599 I slot print_timing: id 3 | task 9367 | prompt eval time = 34783.66 ms / 780 tokens ( 44.59 ms per token, 22.42 tokens per second) 71.09.275.603 I slot print_timing: id 3 | task 9367 | eval time = 1928.53 ms / 2 tokens ( 1928.53 ms per token, 0.52 tokens per second) 71.09.275.604 I slot print_timing: id 3 | task 9367 | total time = 36712.19 ms / 782 tokens 71.09.275.604 I slot print_timing: id 3 | task 9367 | graphs reused = 7888 71.09.275.604 I slot print_timing: id 3 | task 9367 | graph reallocs = 0 / 0 (same size) / (changed size) 71.09.275.641 I slot release: id 3 | task 9367 | stop processing: n_tokens = 781, truncated = 0 71.10.601.112 I slot print_timing: id 1 | task 9370 | prompt eval time = 28060.41 ms / 691 tokens ( 40.61 ms per token, 24.63 tokens per second) 71.10.601.116 I slot print_timing: id 1 | task 9370 | eval time = 1325.90 ms / 2 tokens ( 1325.90 ms per token, 0.75 tokens per second) 71.10.601.116 I slot print_timing: id 1 | task 9370 | total time = 29386.32 ms / 693 tokens 71.10.601.117 I slot print_timing: id 1 | task 9370 | graphs reused = 7888 71.10.601.117 I slot print_timing: id 1 | task 9370 | graph reallocs = 0 / 0 (same size) / (changed size) 71.10.601.151 I slot release: id 1 | task 9370 | stop processing: n_tokens = 692, truncated = 0 71.10.601.356 I slot print_timing: id 2 | task 9371 | prompt eval time = 28060.57 ms / 749 tokens ( 37.46 ms per token, 26.69 tokens per second) 71.10.601.359 I slot print_timing: id 2 | task 9371 | eval time = 1325.93 ms / 2 tokens ( 1325.93 ms per token, 0.75 tokens per second) 71.10.601.359 I slot print_timing: id 2 | task 9371 | total time = 29386.50 ms / 751 tokens 71.10.601.359 I slot print_timing: id 2 | task 9371 | graphs reused = 7888 71.10.601.360 I slot print_timing: id 2 | task 9371 | graph reallocs = 0 / 0 (same size) / (changed size) 71.10.601.388 I slot release: id 2 | task 9371 | stop processing: n_tokens = 750, truncated = 0 71.10.601.394 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 71.10.601.456 I slot launch_slot_: id 1 | task 9379 | processing task, is_child = 0 71.10.601.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 849.168 MiB) 71.10.660.633 I slot print_timing: id 0 | task 9376 | prompt processing, n_tokens = 196, progress = 0.28, t = 3.23 s / 60.62 tokens per second 71.13.251.104 I slot print_timing: id 0 | task 9376 | prompt processing, n_tokens = 571, progress = 0.80, t = 5.88 s / 97.05 tokens per second 71.18.547.142 I slot print_timing: id 0 | task 9376 | prompt processing, n_tokens = 708, progress = 0.99, t = 11.18 s / 63.33 tokens per second 71.18.844.448 I slot print_timing: id 1 | task 9379 | prompt eval time = 7873.18 ms / 107 tokens ( 73.58 ms per token, 13.59 tokens per second) 71.18.844.454 I slot print_timing: id 1 | task 9379 | eval time = 297.31 ms / 2 tokens ( 297.31 ms per token, 3.36 tokens per second) 71.18.844.454 I slot print_timing: id 1 | task 9379 | total time = 8170.49 ms / 109 tokens 71.18.844.455 I slot print_timing: id 1 | task 9379 | graphs reused = 7888 71.18.844.455 I slot print_timing: id 1 | task 9379 | graph reallocs = 0 / 0 (same size) / (changed size) 71.18.844.489 I slot release: id 1 | task 9379 | stop processing: n_tokens = 679, truncated = 0 71.18.947.061 I slot print_timing: id 0 | task 9376 | prompt eval time = 11476.51 ms / 712 tokens ( 16.12 ms per token, 62.04 tokens per second) 71.18.947.064 I slot print_timing: id 0 | task 9376 | eval time = 102.79 ms / 2 tokens ( 102.79 ms per token, 9.73 tokens per second) 71.18.947.065 I slot print_timing: id 0 | task 9376 | total time = 11579.30 ms / 714 tokens 71.18.947.065 I slot print_timing: id 0 | task 9376 | graphs reused = 7888 71.18.947.065 I slot print_timing: id 0 | task 9376 | graph reallocs = 0 / 0 (same size) / (changed size) 71.18.947.097 I slot release: id 0 | task 9376 | stop processing: n_tokens = 713, truncated = 0 71.21.829.100 I srv operator(): operator(): cleaning up before exit...